refactor: merge attention-filters into check-phase skill

Consolidate the attention-filters skill (122 lines) into check-phase,
reducing check-phase from 234 to 110 lines. Removed verbose bash code
blocks, 30-line consolidated output example, re-check protocol (belongs
in act-phase), and motivational section. Updated all references in
README, plugin.json, using-archeflow, and colette-bridge.

.archeflow/config.yaml

@@ -1,7 +1,10 @@
 # ArcheFlow Configuration
 # Copy to your project's .archeflow/config.yaml and customize
 
-version: "0.6.0"
+version: "0.7.0"
+
+# Strategy — execution shape: pdca (cyclic), pipeline (linear), auto (task-based selection)
+strategy: auto
 
 # Budget
 costs:

.claude-plugin/marketplace.json

@@ -0,0 +1,16 @@
+{
+  "name": "claude-archeflow-plugin",
+  "description": "ArcheFlow plugin marketplace",
+  "plugins": [
+    {
+      "name": "archeflow",
+      "description": "Multi-agent orchestration with Jungian archetypes. PDCA quality cycles, shadow detection, git worktree isolation.",
+      "version": "0.3.0",
+      "path": ".",
+      "keywords": [
+        "orchestration", "multi-agent", "archetypes", "pdca",
+        "code-review", "quality", "worktrees", "shadow-detection"
+      ]
+    }
+  ]
+}

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "archeflow",
   "description": "Multi-agent orchestration with Jungian archetypes. PDCA quality cycles, shadow detection, git worktree isolation. Zero dependencies — works with any Claude Code session.",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "author": {
     "name": "Chris Nennemann"
   },
@@ -15,7 +15,7 @@
   ],
   "skills": [
     "run", "orchestration", "plan-phase", "do-phase", "check-phase", "act-phase",
-    "shadow-detection", "attention-filters", "convergence", "artifact-routing",
+    "shadow-detection", "convergence", "artifact-routing",
     "process-log", "memory", "effectiveness", "progress",
     "colette-bridge", "git-integration", "multi-project",
     "custom-archetypes", "workflow-design", "domains", "cost-tracking",

CHANGELOG.md

@@ -2,6 +2,16 @@
 
 All notable changes to ArcheFlow are documented in this file.
 
+## [0.7.0] -- 2026-04-04
+
+### Added
+- Context isolation protocol in attention-filters skill and all 7 agent personas — agents receive only orchestrator-constructed context, no session bleed or cross-agent contamination
+- Structured status tokens (`STATUS: DONE`, `DONE_WITH_CONCERNS`, `NEEDS_CONTEXT`, `BLOCKED`) for all agents with orchestrator parsing protocol in run skill
+- Evidence-gated verification in check-phase — CRITICAL/WARNING findings require concrete evidence (command output, code citations, reproduction steps); banned speculative phrases auto-downgrade to INFO
+- Plan granularity constraint in plan-phase and Creator — each change item must be a 2-5 minute task with exact file path, code block, and verify command
+- Strategy abstraction with `pdca` (cyclic) and `pipeline` (linear) execution strategies, auto-selection by task type, and pipeline execution flow in run skill
+- Experimental status and interdisciplinary framing in README
+
 ## [0.6.0] -- 2026-04-04
 
 ### Added

CLAUDE.md

@@ -0,0 +1,71 @@
+# archeflow — Multi-Agent Orchestration Plugin for Claude Code
+
+Workspace-level orchestration: parallel agent teams across project portfolios, PDCA cycles with Jungian archetype roles, sprint runner, and post-implementation review. Installed as a Claude Code plugin.
+
+## Tech Stack
+
+- **Runtime:** Bash (lib scripts) + Claude Code skill system (Markdown skills)
+- **No build step, no dependencies** — pure bash + markdown
+- **Plugin format:** Claude Code plugin (skills/, hooks/, agents/, templates/)
+
+## Key Commands
+
+```bash
+# Use via Claude Code slash commands:
+/af-sprint          # Main mode: work the queue across projects
+/af-run <task>      # Deep orchestration with PDCA cycles
+/af-review          # Post-implementation security/quality review
+/af-status          # Current run status
+/af-init            # Initialize ArcheFlow in a project
+/af-score           # Archetype effectiveness scores
+/af-memory          # Cross-run lesson memory
+/af-report          # Full process report
+/af-fanout          # Colette book fanout via agents
+```
+
+## Architecture
+
+```
+skills/                 Slash command implementations (one dir per skill)
+  sprint/               /af-sprint — queue-driven parallel agent runner
+  run/                  /af-run — PDCA orchestration
+  review/               /af-review — Guardian-led code review
+  plan-phase/           PDCA Plan phase
+  do-phase/             PDCA Do phase
+  check-phase/          PDCA Check phase
+  act-phase/            PDCA Act phase
+  memory/               Cross-run lessons learned
+  cost-tracking/        Token/cost awareness
+  domains/              Domain detection (code, writing, research)
+  ...                   ~25 skill directories
+hooks/
+  hooks.json            Hook definitions
+  session-start/        Auto-activation on session start
+agents/                 Archetype agent definitions
+  explorer.md           Divergent thinking, research
+  creator.md            Design, architecture
+  maker.md              Implementation
+  guardian.md            Security, risk, quality gates
+  sage.md               Wisdom, patterns, trade-offs
+  skeptic.md            Devil's advocate
+  trickster.md          Edge cases, unconventional approaches
+lib/                    Bash helper scripts (git, DAG, events, progress, etc.)
+templates/bundles/      Pre-configured workflow bundles
+docs/                   Roadmap, dogfood notes, test reports
+```
+
+## Domain Rules
+
+- Skills are Markdown files with frontmatter — follow existing skill format exactly
+- Agents are archetype personas — maintain their distinct voice and perspective
+- Dogfood observations go to `archeflow/.archeflow/memory/lessons.jsonl`
+- Cost tracking: prefer cheap models for bulk ops, expensive for creative/review
+- PDCA cycle order is mandatory: Plan -> Do -> Check -> Act
+
+## Do NOT
+
+- Add runtime dependencies — this must stay zero-dependency
+- Change archetype personalities without updating all referencing skills
+- Skip the Check phase in PDCA cycles (quality gate)
+- Modify hooks.json format without testing plugin reload
+- Use ArcheFlow to orchestrate simple single-file tasks (overhead not justified)

README.md

@@ -1,16 +1,37 @@
-# ArcheFlow -- Multi-Agent Orchestration for Claude Code
+# ArcheFlow -- Workspace Orchestration for Claude Code
 
-**Structured quality through archetypal collaboration.** ArcheFlow coordinates multiple Claude Code agents through PDCA cycles, where each agent embodies a Jungian archetype with defined strengths and known failure modes.
+**Run parallel agent teams across your entire project portfolio.** ArcheFlow reads a task queue, spawns agents across multiple projects simultaneously, collects results, commits, and keeps going. Built for developers managing 10-30 repos who want throughput, not ceremony.
 
 Zero dependencies. No build step. Install and go.
 
+> **Status: Experimental.** ArcheFlow is a research prototype exploring the intersection of
+> analytical psychology (Jungian archetypes), process engineering (PDCA cycles), and
+> multi-agent software engineering. It is functional and actively developed, but not production-ready.
+> APIs, skill formats, and orchestration behavior may change between versions.
+
 ## What It Does
 
-Large coding tasks benefit from multiple perspectives, but "just spawn more agents" creates chaos. Agents duplicate work, miss each other's output, argue in circles, or go rogue. The problem is not intelligence -- it is coordination.
+ArcheFlow solves three problems:
 
-ArcheFlow solves this by giving each agent an *archetype*: a behavioral protocol that defines what the agent cares about, what context it receives, and how its output feeds into the next phase. Seven archetypes collaborate through **Plan-Do-Check-Act cycles**, where each iteration builds on structured feedback from the last. No unreviewed code reaches your main branch.
+**1. Workspace Sprint Runner** (`/af-sprint`) -- The primary mode. Reads your task queue, picks the highest-priority items across different projects, spawns 3-5 agents in parallel, collects results, commits+pushes, and immediately starts the next batch. Turns a 25-item backlog into done work while you watch (or don't).
 
-The key insight: archetypes are not just system prompts. Each one has a **virtue** (its unique contribution) and a **shadow** (the dysfunction it falls into when pushed too far). ArcheFlow monitors for shadow activation and course-corrects automatically -- replacing an agent that blocks everything, reining in one that researches forever, or escalating when a maker goes off-script.
+**2. Post-Implementation Review** (`/af-review`) -- Run security and quality review on any diff, branch, or commit range. No planning, no implementation orchestration -- just Guardian analysis of what could go wrong. The highest-ROI mode for catching design-level bugs that linters miss.
+
+**3. Deep Orchestration** (`/af-run`) -- For complex tasks that need structured exploration, design, implementation, and multi-perspective review. Uses archetypal roles (Explorer, Creator, Maker, Guardian) through PDCA cycles. Best for security-sensitive changes, multi-module refactors, and creative writing.
+
+### When to use what
+
+| Situation | Command | Why |
+|-----------|---------|-----|
+| Work the backlog | `/af-sprint` | Parallel agents, maximum throughput |
+| Review before merging | `/af-review` | Catch design bugs, not style nits |
+| Complex feature (L/XL) | `/af-run` or `feature-dev` | Structured exploration + review |
+| Simple fix (S/M) | Just do it | No orchestration overhead needed |
+| Creative writing | `/af-run --domain writing` | Archetypes shine here -- no linters exist for prose |
+
+### What ArcheFlow is NOT
+
+ArcheFlow is not a feature development tool. For single-feature implementation with user interaction at every step (clarify requirements, choose architecture, review), use Claude Code's `feature-dev` plugin or work directly. ArcheFlow adds value through **parallel execution across projects** and **domain-specific quality review** (writing, research), not by competing with single-task development tools.
 
 ## Quick Start
 
@@ -54,50 +75,61 @@ After installing, run `/reload-plugins` or restart Claude Code. ArcheFlow activa
 - `--scope project` — only in the current project
 - `--scope local` — only in the current directory
 
-### 2. Run your first orchestration
+### 2. Run your first sprint
-
-Just describe a task. ArcheFlow activates automatically for multi-file changes:
 
 ```
-> Add input validation to all API endpoints
+> /af-sprint
 ```
 
-Or invoke it explicitly:
+ArcheFlow reads your task queue (`docs/orchestra/queue.json`), picks the highest-priority items, and spawns parallel agents:
 
 ```
-> archeflow:run "Add JWT authentication" --workflow standard
+── af-sprint: Batch 1 ──────────────────────────
+  🔸 writing.colette    config parser expansion    [P2, M]  running
+  🔸 product.jobradar   search API endpoint        [P3, M]  running
+  🔸 tool.git-alm       SVG export + minimap       [P3, M]  running
+  🔸 product.game-factory completion tracking      [P3, S]  running
+────────────────────────────────────────────────
+
+[5 min later]
+
+── Batch 1 complete ────────────────────────────
+  ✓ writing.colette    config parser              done (3m24s)
+  ✓ product.jobradar   search API                 done (5m01s)
+  ✓ tool.git-alm       SVG export                 done (4m30s)
+  ✓ product.game-factory tracking                 done (2m15s)
+
+4 tasks · 4 projects · all committed + pushed
+Next batch: 2 items ready → dispatching...
+────────────────────────────────────────────────
 ```
 
-### 3. What happens
+### 3. Review before merging
-
-ArcheFlow selects a workflow (fast, standard, or thorough) and runs a PDCA cycle:
 
 ```
-Plan  --> Explorer researches codebase context, Creator designs a proposal
+> /af-review --branch feat/batch-api
-Do    --> Maker implements in an isolated git worktree
-Check --> Reviewers assess in parallel (Guardian, Skeptic, Sage, Trickster)
-Act   --> All approved? Merge. Issues found? Cycle back with structured feedback.
-
-Each cycle catches what the last one missed.
 ```
 
-Progress is visible in real time:
+Guardian analyzes the diff for error handling gaps, security issues, and data loss scenarios:
 
 ```
---- ArcheFlow: Add JWT authentication ---------
+── af-review: writing.colette ─────────────────
-Workflow: standard (2 cycles max)
+🛡️ Guardian: 2 findings (1 HIGH, 1 MEDIUM)
-
+  [HIGH] Timeout marks variant as done — loses batch state (fanout.py:552)
-🔍 [Plan] Explorer researching...        done (35s)
+  [MEDIUM] No JSON error handling on corrupted state (batch.py:310)
-🏗️ [Plan] Creator designing proposal...   done (25s, confidence: 0.8)
+────────────────────────────────────────────────
-⚒️ [Do]   Maker implementing...           done (90s, 4 files, 8 tests)
-🛡️ [Check] Guardian reviewing...          APPROVED
-🤔 [Check] Skeptic challenging...          APPROVED (1 INFO)
-📚 [Check] Sage reviewing...              APPROVED
-   [Act]  All approved -- merging...       merged to main
-
---- Complete: 3m 10s, 1 cycle -----------------
 ```
 
+### 4. Deep orchestration (when needed)
+
+For complex, security-sensitive, or creative tasks:
+
+```
+> /af-run "Add JWT authentication" --workflow standard
+```
+
+This runs the full PDCA cycle with archetypal roles. See "Deep Orchestration" below for details.
+
 ## The Seven Archetypes
 
 | Archetype | Phase | Virtue | Shadow | Role |
@@ -132,7 +164,6 @@ ArcheFlow ships with 24 skills organized by function.
 | Skill | Description |
 |-------|-------------|
 | `archeflow:shadow-detection` | Quantitative dysfunction detection and automatic correction |
-| `archeflow:attention-filters` | Context optimization per archetype -- each agent gets only what it needs |
 | `archeflow:convergence` | Detects convergence, stalling, and oscillation in multi-cycle runs |
 | `archeflow:artifact-routing` | Inter-phase artifact protocol -- naming, storage, routing, archiving |
 
@@ -326,7 +357,6 @@ archeflow/
 │   ├── check-phase/             #   Check protocols
 │   ├── act-phase/               #   Act phase decision logic
 │   ├── shadow-detection/        #   Dysfunction detection
-│   ├── attention-filters/       #   Context optimization
 │   ├── convergence/             #   Cycle convergence detection
 │   ├── artifact-routing/        #   Inter-phase artifact protocol
 │   ├── process-log/             #   Event-sourced JSONL logging

agents/creator.md

@@ -46,8 +46,16 @@ For the full output format (including Mini-Reflect, Alternatives Considered, and
 | <option B> | <reason> |
 
 ### Changes
-1. **`path/file.ext`** — What changes and why
+1. **`path/file.ext:line`** — What changes and why
+   ```language
+   <target code state>
+   ```
+   **Verify:** `<command to confirm correctness>`
 2. **`path/test.ext`** — What tests to add
+   ```language
+   <test code>
+   ```
+   **Verify:** `<test command>`
 
 ### Test Strategy
 - <specific test cases>
@@ -67,11 +75,24 @@ For the full output format (including Mini-Reflect, Alternatives Considered, and
 ```
 
 ## Rules
+- **Context isolation:** You receive only what the orchestrator provides. Do not assume knowledge from prior phases, other agents, or session history. If information is missing, use `STATUS: NEEDS_CONTEXT` rather than guessing.
 - Be decisive. One proposal, not three alternatives (but list alternatives you rejected).
 - Name every file. The Maker needs exact paths.
 - Scope ruthlessly. Adjacent problems go under "Not Doing."
 - Include test strategy. No proposal is complete without it.
+- **Granularity:** Each change item must be a 2-5 minute task with exact file path, code block showing the target state, and a verify command. If an item would take >5 minutes, split it. If a non-trivial task has <2 items, you under-specified.
 - Any Confidence axis < 0.5? Flag it — the orchestrator may pause or escalate.
 
+## Status Token
+
+End your output with exactly one status line:
+
+- `STATUS: DONE` — proposal ready with confidence scores
+- `STATUS: DONE_WITH_CONCERNS` — proposal ready but low confidence on one or more axes
+- `STATUS: NEEDS_CONTEXT` — cannot proceed without additional information (describe what is missing)
+- `STATUS: BLOCKED` — unresolvable obstacle (describe it)
+
+This line MUST be the last non-empty line of your output.
+
 ## Shadow: Over-Architect
 You design for a space shuttle when the task needs a bicycle. Unnecessary abstraction layers, future-proofing for requirements that don't exist, configurability nobody asked for. If the proposal has more infrastructure than business logic — simplify. Design for the current order of magnitude, not 100x.

agents/explorer.md

@@ -45,9 +45,21 @@ You see the landscape before anyone acts. You map dependencies, spot existing pa
 ```
 
 ## Rules
+- **Context isolation:** You receive only what the orchestrator provides. Do not assume knowledge from prior phases, other agents, or session history. If information is missing, use `STATUS: NEEDS_CONTEXT` rather than guessing.
 - Synthesize, don't dump. Raw file lists are useless.
 - Stay focused on the task. Interesting tangents go in a "See Also" footnote, not the main report.
 - Cap your research at 15 files. If you need more, the task is too broad.
 
+## Status Token
+
+End your output with exactly one status line:
+
+- `STATUS: DONE` — research complete, findings ready
+- `STATUS: DONE_WITH_CONCERNS` — research complete but gaps remain (noted in output)
+- `STATUS: NEEDS_CONTEXT` — cannot proceed without additional information (describe what is missing)
+- `STATUS: BLOCKED` — unresolvable obstacle (describe it)
+
+This line MUST be the last non-empty line of your output.
+
 ## Shadow: Rabbit Hole
 Your curiosity becomes compulsive investigation. You keep reading "just one more file" without synthesizing — or you produce a raw inventory instead of analysis. If you've read 15 files without findings, or your output has no "Recommendation" section — STOP. Synthesize what you have. A dump is not research. Good-enough now beats perfect never.

agents/guardian.md

@@ -36,9 +36,22 @@ You see attack surfaces others walk past. You calibrate your response to actual
 - **INFO** — Minor hardening opportunity.
 
 ## Rules
+- **Context isolation:** You receive only what the orchestrator provides. Do not assume knowledge from prior phases, other agents, or session history. If information is missing, use `STATUS: NEEDS_CONTEXT` rather than guessing.
 - APPROVED = zero CRITICAL findings
 - Every finding needs a suggested fix, not just a complaint
+- **Evidence required:** Every CRITICAL or WARNING must cite a specific command output, exit code, or exact code with file path and line numbers. Findings without evidence are downgraded to INFO by the orchestrator.
 - Be rigorous but practical — flag real risks, not science fiction
 
+## Status Token
+
+End your output with exactly one status line:
+
+- `STATUS: DONE` — review complete, verdict and findings ready
+- `STATUS: DONE_WITH_CONCERNS` — review complete but some areas could not be fully assessed
+- `STATUS: NEEDS_CONTEXT` — cannot proceed without additional information (describe what is missing)
+- `STATUS: BLOCKED` — unresolvable obstacle (describe it)
+
+This line MUST be the last non-empty line of your output.
+
 ## Shadow: Paranoid
 Your risk awareness becomes blocking everything. Every finding is CRITICAL, every risk is existential, and you reject without suggesting how to fix it. Ask: "Would a senior engineer block this PR for this?" If no, downgrade. Every rejection MUST include a specific fix — if you can't suggest one, you don't understand the problem well enough to reject.

agents/maker.md

@@ -45,6 +45,7 @@ You turn plans into working, tested, committed code. Small steps, steady progres
 ```
 
 ## Rules
+- **Context isolation:** You receive only what the orchestrator provides. Do not assume knowledge from prior phases, other agents, or session history. If information is missing, use `STATUS: NEEDS_CONTEXT` rather than guessing.
 - **Isolation:** Always spawn with `isolation: "worktree"` to work in a dedicated git worktree.
 - Follow the proposal. Don't redesign.
 - Tests before implementation. Always.
@@ -53,5 +54,16 @@ You turn plans into working, tested, committed code. Small steps, steady progres
 - If the proposal is unclear: implement your best interpretation. Note what you assumed.
 - If you find a blocker: document it and stop. Don't silently work around it.
 
+## Status Token
+
+End your output with exactly one status line:
+
+- `STATUS: DONE` — implementation complete, all commits made
+- `STATUS: DONE_WITH_CONCERNS` — implementation complete but assumptions were made (noted in output)
+- `STATUS: NEEDS_CONTEXT` — cannot proceed without additional information (describe what is missing)
+- `STATUS: BLOCKED` — unresolvable obstacle (describe it)
+
+This line MUST be the last non-empty line of your output.
+
 ## Shadow: Rogue
 Your bias for action becomes reckless shipping. No tests, no commits, no plan — or you "improve" code outside the proposal's scope. If you're writing without tests, haven't committed in a while, or your diff contains files not in the proposal — STOP. Read the proposal. Write a test. Commit. Revert extras.

agents/sage.md

@@ -46,10 +46,23 @@ You see the forest, not just the trees. "Will a new team member understand this
 - Are existing docs/comments still accurate after the change?
 
 ## Rules
+- **Context isolation:** You receive only what the orchestrator provides. Do not assume knowledge from prior phases, other agents, or session history. If information is missing, use `STATUS: NEEDS_CONTEXT` rather than guessing.
 - APPROVED = code is readable, tested, consistent, and complete
 - REJECTED = significant quality issues that affect maintainability
+- **Evidence required:** Quality findings must cite specific code (file:line, exact construct) or measurable criteria. Do not raise vague suggestions — if you cannot point to the code, do not raise the finding.
 - Focus on the next 6 months. Not the next 6 years.
 - Your review should be shorter than the code change. If it's not, you're over-reviewing.
 
+## Status Token
+
+End your output with exactly one status line:
+
+- `STATUS: DONE` — review complete, verdict and findings ready
+- `STATUS: DONE_WITH_CONCERNS` — review complete but some quality dimensions could not be assessed
+- `STATUS: NEEDS_CONTEXT` — cannot proceed without additional information (describe what is missing)
+- `STATUS: BLOCKED` — unresolvable obstacle (describe it)
+
+This line MUST be the last non-empty line of your output.
+
 ## Shadow: Bureaucrat
 Your thoroughness becomes bloat. Your review is longer than the code change, you're suggesting improvements to untouched code, or producing deep-sounding analysis without actionable findings. If you can't state the consequence of NOT fixing it, don't raise it. If a finding doesn't end with a specific action, delete it. Insight without action is noise.

agents/skeptic.md

@@ -33,11 +33,24 @@ You make the implicit explicit. "The plan assumes X — but does X actually hold
 ```
 
 ## Rules
+- **Context isolation:** You receive only what the orchestrator provides. Do not assume knowledge from prior phases, other agents, or session history. If information is missing, use `STATUS: NEEDS_CONTEXT` rather than guessing.
 - Every challenge MUST include an alternative. "This might not work" alone is not helpful.
 - Limit to 3-5 challenges. More than 7 is shadow behavior.
+- **Evidence required:** Every challenge must reference specific code (file:line) or describe a concrete scenario with reproduction steps. Vague concerns without evidence are downgraded to INFO by the orchestrator.
 - Stay in scope. Challenge the task's assumptions, not the universe's.
 - APPROVED = no fundamental design flaws
 - REJECTED = the approach is wrong, and you have a better one
 
+## Status Token
+
+End your output with exactly one status line:
+
+- `STATUS: DONE` — review complete, verdict and findings ready
+- `STATUS: DONE_WITH_CONCERNS` — review complete but some assumptions could not be verified
+- `STATUS: NEEDS_CONTEXT` — cannot proceed without additional information (describe what is missing)
+- `STATUS: BLOCKED` — unresolvable obstacle (describe it)
+
+This line MUST be the last non-empty line of your output.
+
 ## Shadow: Paralytic
 Your critical thinking becomes inability to approve anything. You list 7+ challenges, chain "what about X?" tangents, or question things outside the task — each plausible alone, none actionable together. STOP. Rank by impact. Keep top 3. Each must include an alternative. Delete the rest.

agents/trickster.md

@@ -39,10 +39,22 @@ You think like an attacker, a clumsy user, a failing network. You find the edges
 ```
 
 ## Rules
+- **Context isolation:** You receive only what the orchestrator provides. Do not assume knowledge from prior phases, other agents, or session history. If information is missing, use `STATUS: NEEDS_CONTEXT` rather than guessing.
 - Test ONLY the changed code, not the entire system
 - Every finding needs exact reproduction steps
 - If you can't break it after 5 serious attempts — APPROVED. The code is resilient.
 - Constructive chaos only. Your goal is quality, not destruction.
 
+## Status Token
+
+End your output with exactly one status line:
+
+- `STATUS: DONE` — review complete, verdict and findings ready
+- `STATUS: DONE_WITH_CONCERNS` — testing complete but some attack vectors could not be exercised
+- `STATUS: NEEDS_CONTEXT` — cannot proceed without additional information (describe what is missing)
+- `STATUS: BLOCKED` — unresolvable obstacle (describe it)
+
+This line MUST be the last non-empty line of your output.
+
 ## Shadow: False Alarm
 You flood with low-signal findings. Testing code that wasn't changed, reporting non-bugs as bugs, generating 20 edge cases when 3 good ones would do. If your findings reference files not in the Maker's diff — delete them. Quality over quantity. Three real findings beat twenty noise.

docs/dogfood-2026-04-04-batch.md

@@ -0,0 +1,181 @@
+# ArcheFlow Dogfood Report #2: Batch API Integration
+
+Date: 2026-04-04
+Task: Wire Anthropic Batch API into Colette's fanout pipeline with CLI commands and state persistence
+Project: writing.colette (Python, 27 modules, 457 tests)
+Complexity: High — 4 files, async API, state persistence, error recovery, CLI commands
+
+## Experimental Setup
+
+Same task, same starting commit, two conditions:
+1. **Baseline**: Plain Claude, no orchestration, single pass
+2. **ArcheFlow**: PDCA standard workflow (Maker + Guardian review)
+
+No Explorer or Creator used this time — task scope was clear enough to skip planning and go directly to Maker + Guardian (effectively a fast workflow).
+
+## Quantitative Comparison
+
+| Metric | Baseline | ArcheFlow | Delta |
+|--------|----------|-----------|-------|
+| Lines added | 189 | 279 | +48% |
+| Files touched | 4 | 4 | same |
+| Time | ~5 min | ~12 min | +140% |
+| Commits | 1 | 4 | cleaner history |
+| Tests written | 1 | 2 | +1 |
+| Tests passing | 13/13 | 14/14 | +1 |
+| Bugs introduced | 0 | 1 | worse |
+| Bugs caught by review | 0 | 5 | better |
+| **Real bugs in final code** | **1** | **0** (after fix) | **ArcheFlow wins** |
+
+## Bug Analysis
+
+### Bugs found only by Guardian (not present in baseline)
+
+| # | Bug | Severity | Impact |
+|---|-----|----------|--------|
+| 3 | `hash()` non-deterministic across processes for chapter index mapping | HIGH | Data loss on resume — chapters mapped to wrong files |
+
+This bug was **introduced by ArcheFlow's Maker** and caught by the Guardian. Baseline used `enumerate(i)` and avoided it entirely. Net: zero value.
+
+### Bugs present in BOTH versions, caught only by Guardian
+
+| # | Bug | Severity | Impact |
+|---|-----|----------|--------|
+| 4 | Timeout marks variant as "done" — permanently loses batch state | HIGH | Silent data loss — timed-out batches can never be resumed |
+
+This is the **key finding**. Both implementations had this design-level bug. Only ArcheFlow's Guardian caught it. Plain Claude missed it because there was no review step.
+
+### Bugs in both, not caught by either initially
+
+| # | Bug | Severity | Impact |
+|---|-----|----------|--------|
+| 1 | API key resolution inconsistency (env vs config) | CRITICAL | Wrong key used under mixed-key environments |
+| 5 | No JSON error handling on corrupted state files | HIGH | Crash on truncated state file |
+
+Guardian flagged these. Baseline would have shipped them silently.
+
+## Qualitative Observations
+
+### Where Guardian added real value
+
+1. **Error path analysis**: Guardian systematically checked "what happens when X fails?" for timeout, cancellation, corruption, and cross-process resume. Plain Claude focused on the happy path.
+2. **Cross-process state**: The `hash()` non-determinism finding required reasoning about Python's hash randomization across interpreter invocations — a subtle runtime property that isn't visible from reading the code in isolation.
+3. **Data loss scenarios**: Finding #4 (timeout → "done" → lost forever) requires understanding the interaction between `wait_and_retrieve`'s timeout branch and the caller's unconditional status assignment. This is a 2-module interaction that single-pass implementation doesn't systematically check.
+
+### Where Guardian added noise
+
+1. **Finding #2 (batch_id validation)**: Technically valid but the Anthropic SDK already rejects malformed IDs. Low practical risk.
+2. **Finding #1 (API key source)**: Valid but matches existing patterns throughout the codebase — flagging it here without flagging it elsewhere is inconsistent.
+
+### The Maker problem
+
+The ArcheFlow Maker introduced a bug (hash-based indexing) that the baseline avoided. This happened because:
+- The Maker was working from a task description, not reading the existing sequential rewrite code as closely
+- The Creator's plan (when used in dogfood #1) over-specified some things and under-specified others
+- Working through an intermediary (plan → implementation) introduces information loss
+
+This is a structural weakness of the PDCA model: the Plan-to-Do handoff can corrupt information.
+
+## Conclusions
+
+### Complexity threshold confirmed
+
+| Task type | Orchestration value |
+|-----------|-------------------|
+| Simple (pattern-following, single file) | **Negative** — adds cost, Maker introduces bugs |
+| Medium (multi-file feature, clear scope) | **Neutral** — extra code but similar outcome |
+| Complex (error handling, state, async, resume) | **Positive** — Guardian catches design-level bugs |
+
+The differentiator is **error path coverage**. Guardian's systematic "what if this fails?" analysis catches bugs that single-pass implementation misses because implementers focus on making things work, not on making failures safe.
+
+### The honest ROI question
+
+For this task: Guardian caught 1 bug the baseline missed (timeout data loss). That bug would have caused real data loss in production when a batch times out. The cost was ~7 extra minutes and a Maker-introduced bug that had to be fixed.
+
+Is preventing a production data loss bug worth 7 extra minutes? Yes. But only because this was a task where data loss was possible. For a pure UI change or a refactor with no persistence, the answer would be no.
+
+---
+
+## Improvement Hypotheses
+
+Based on both dogfood runs, here are concrete hypotheses about how to improve ArcheFlow's value-to-cost ratio:
+
+### H1: Guardian-Only Mode (skip Plan/Do orchestration)
+
+**Observation**: In both dogfoods, the Maker produced equivalent-or-worse code than plain Claude. The value came entirely from the Guardian review.
+
+**Hypothesis**: A "review-only" mode where the user implements normally and then runs ArcheFlow as a post-implementation review would capture the Guardian's value without the Maker's overhead.
+
+**Test**: Implement the same task plain, then run `af-review` (Guardian + Skeptic on the diff). Compare bug catch rate to full PDCA.
+
+**Expected outcome**: Same bug catch rate, ~60% less cost.
+
+### H2: Pre-Implementation Threat Modeling (Guardian before Maker)
+
+**Observation**: Guardian found error-handling bugs (timeout, corruption) that the Maker didn't anticipate. If Guardian's "what could go wrong?" analysis ran BEFORE implementation, the Maker could build in error handling from the start.
+
+**Hypothesis**: Running a lightweight Guardian analysis on the Creator's plan (not the code) would produce a "threat list" that the Maker addresses during implementation, eliminating the need for a fix cycle.
+
+**Sequence**: Creator → Guardian(plan) → Maker(plan + threats) → Guardian(code)
+
+**Expected outcome**: Fewer Maker-introduced bugs, shorter fix cycle, Guardian's code review focuses on implementation correctness rather than missing error paths.
+
+### H3: Differential Review (only review what the Maker DIDN'T get from the plan)
+
+**Observation**: The Maker copies most of the plan correctly. The bugs are in the gaps — things the plan didn't specify (error handling, cross-process state, timeout recovery).
+
+**Hypothesis**: Instead of reviewing the entire diff, focus the Guardian on the delta between the plan and the implementation — what the Maker added, changed, or skipped that wasn't in the plan.
+
+**Test**: Extract the plan's explicit instructions, diff against the implementation, and give Guardian only the unplanned additions.
+
+**Expected outcome**: Higher signal-to-noise ratio (fewer false positives on code that correctly follows the plan), focused attention on the dangerous gaps.
+
+### H4: Project Convention Calibration (reduce false positives)
+
+**Observation**: Guardian flagged API key handling (finding #1) and batch_id validation (finding #2) — both valid in absolute terms but inconsistent with the project's existing patterns. The project doesn't validate IDs or centralize key management anywhere else.
+
+**Hypothesis**: Injecting a "project conventions" summary before Guardian review (e.g., "this project uses env vars for API keys, does not validate external IDs, handles errors via outer try/except") would let Guardian calibrate its expectations and only flag deviations from convention, not the convention itself.
+
+**Test**: Run Guardian with and without convention context on the same diff. Count false positives.
+
+**Expected outcome**: 30-50% reduction in noise findings without missing real bugs.
+
+### H5: Abandon PDCA for Implementation, Keep It for Review
+
+**Observation**: Across both dogfoods, the cycle-back mechanism (Plan→Do→Check→Act→cycle back) never triggered. All reviews were APPROVED_WITH_FIXES, and fixes were applied in a single pass. The cyclic model added structural overhead (event tracking, artifact routing, convergence detection) that was never used.
+
+**Hypothesis**: For most tasks, a linear pipeline (implement → multi-reviewer check → targeted fix) is sufficient. Reserve cyclic PDCA for tasks where reviewers fundamentally reject the approach (not just the implementation).
+
+**Test**: Compare PDCA standard (cycle-back enabled) vs pipeline (no cycle-back) on 10 tasks. Measure: how often does cycle-back actually improve the outcome?
+
+**Expected outcome**: Cycle-back triggers in <10% of tasks. Pipeline matches PDCA quality for 90%+ of cases at lower cost.
+
+### H6: Evidence-Gated Findings Actually Work
+
+**Observation**: Of Guardian's 5 findings in this dogfood, 3 were substantive (timeout data loss, hash non-determinism, no JSON error handling) and 2 were low-value (API key pattern, batch_id format). The substantive ones cited specific code paths and failure scenarios. The low-value ones cited general principles without evidence of actual exploitation.
+
+**Hypothesis**: The evidence-gating mechanism added in v0.7.0 (ban hedged phrases, require command output or code citation) would have automatically downgraded finding #2 ("could corrupt log output") while preserving findings #3 and #4 (which cite specific code paths and failure mechanisms).
+
+**Test**: Re-run the Guardian review with evidence-gating active. Count how many findings survive vs. get downgraded.
+
+**Expected outcome**: 1-2 findings correctly downgraded, 0 real bugs missed.
+
+### H7: Shadow Detection for the Maker
+
+**Observation**: The Maker introduced a bug (hash-based indexing) because it deviated from the existing codebase pattern (enumerate-based indexing). This is the "Rogue" shadow — the Maker going off-script from what the codebase already does.
+
+**Hypothesis**: A pre-commit check that compares the Maker's implementation against the existing codebase patterns (e.g., "how are chapter indices computed elsewhere in fanout.py?") would catch Rogue deviations before the Guardian review.
+
+**Test**: Add a "pattern conformance" check to the Do phase that greps for how the modified variables/functions are used elsewhere in the file.
+
+**Expected outcome**: Catches Rogue shadow bugs at implementation time rather than review time, saving a review cycle.
+
+---
+
+## Recommended Next Steps (Priority Order)
+
+1. **H1**: Build `af-review` mode (Guardian-only on existing diff) — lowest effort, highest expected ROI
+2. **H4**: Project convention injection — reduce noise without missing signal
+3. **H2**: Pre-implementation threat modeling — address the root cause of missing error handling
+4. **H5**: Default to pipeline strategy, reserve PDCA for rejections
+5. **H7**: Maker pattern conformance check — reduce Maker-introduced bugs

docs/dogfood-2026-04-04.md

@@ -0,0 +1,78 @@
+# ArcheFlow Dogfood Report: Colette Expose/Pitch Generation
+
+Date: 2026-04-04
+Task: Implement expose and pitch generation steps in Colette's fanout pipeline
+Project: writing.colette (Python, 27 modules, 457 tests)
+
+## Task Description
+
+The fanout pipeline in `src/colette/fanout.py` had two placeholder steps (`generate_expose`, `generate_pitch`) that logged "not yet implemented". The task was to replace them with real LLM-powered implementations that generate publishing proposals and pitch letters.
+
+## Conditions
+
+| Condition | Strategy | Agents | Time | Lines |
+|-----------|----------|--------|------|-------|
+| **Plain Claude** (no orchestration) | None | 0 | ~3 min | 107 (+75 impl, +32 test) |
+| **ArcheFlow PDCA** (standard workflow) | pdca | 4 (Explorer, Creator, Maker, Guardian) | ~15 min | 230 (+145 impl, +85 test) |
+
+## Findings
+
+### Bugs introduced
+
+| Condition | Bug | Caught by | Severity |
+|-----------|-----|-----------|----------|
+| Plain Claude | None | N/A | N/A |
+| ArcheFlow | `task_type`/`file_path` kwargs passed to `LLMClient.create()` but only exist on `GuardedLLMClient` | Guardian review | CRITICAL (runtime crash on non-guarded clients) |
+
+**Key observation:** ArcheFlow's Maker introduced a bug that plain Claude avoided. The Guardian caught it, but the net result was: introduce bug + catch bug = extra work for the same outcome.
+
+### Code comparison
+
+| Metric | Plain Claude | ArcheFlow |
+|--------|-------------|-----------|
+| Implementation lines | 75 | 145 |
+| Test lines | 32 | 85 |
+| LLMClient compatibility | Clean (protocol args only) | Needed fix (extra kwargs) |
+| Prompt detail | Adequate (10 sections listed) | More detailed (explicit section descriptions) |
+| Defensive coding | Minimal (follows existing patterns) | More (mkdir guards, fallback paths) |
+| Test thoroughness | Basic (file existence, call count) | More thorough (token accumulation, error states) |
+
+### Process overhead
+
+| Phase | Time | Value added |
+|-------|------|-------------|
+| Explorer research | ~60s | Low — task was well-scoped, pattern was obvious from reading 2 lines |
+| Creator proposal | ~45s | Low — 300-line plan for 75-line task, mostly restated what the code already showed |
+| Maker implementation | ~90s | Same as plain Claude, but produced more verbose code + a bug |
+| Guardian review | ~30s | Mixed — caught 1 real bug (out of 5 findings, 80% noise) |
+
+### Why plain Claude won
+
+1. **Pattern-following task.** Two placeholder functions, one existing pattern to copy. No ambiguity, no design decisions, no security concerns.
+2. **Direct protocol reading.** Plain Claude checked the `LLMClient.create()` signature and used only standard args. The Maker, working from the Creator's plan (which didn't mention the protocol), used extra kwargs it saw in the `GuardedLLMClient`.
+3. **Less indirection = fewer errors.** The Creator-to-Maker handoff introduced information loss. The Creator specified "call llm_client.create()" but didn't specify the exact signature constraints. Plain Claude read the source of truth directly.
+
+### When ArcheFlow would have been worth it
+
+This task had none of these signals:
+- Ambiguous requirements (need Explorer)
+- Multiple valid approaches (need Creator to evaluate)
+- Security-sensitive code (need Guardian for real threats)
+- Cross-cutting changes (5+ files, interaction risks)
+- Unfamiliar codebase (need research phase)
+
+### Improvement opportunities
+
+1. **Auto-select should skip orchestration** for pattern-following tasks (placeholder + existing pattern in same file)
+2. **Creator compact mode** — for simple tasks, emit a 10-line diff-style plan, not a 300-line essay
+3. **Explorer budget cap** — 60s max for single-file tasks
+4. **Guardian calibration** — inject project conventions to reduce false positives from 80% to ~40%
+5. **Baseline capture** — run the same task without ArcheFlow to enable A/B comparison
+
+## Conclusion
+
+For this specific task (simple, pattern-following, single-file, well-scoped), ArcheFlow added cost without adding quality. Plain Claude was faster, produced less code, and avoided a bug that the Maker introduced.
+
+This is not a failure of ArcheFlow's design — it's a calibration problem. The auto-select heuristic should have detected this as a skip-orchestration task. The complexity threshold for ArcheFlow activation needs to be higher than "touches 2+ files."
+
+**Honest assessment:** ArcheFlow's value-add starts at tasks requiring genuine design decisions, security review, or cross-module coordination. Below that threshold, it's ceremony.

docs/roadmap.md

@@ -2,6 +2,14 @@
 
 ## Completed
 
+### v0.7.0 (2026-04-04)
+- [x] Context isolation protocol for attention filters and all agent personas
+- [x] Structured status tokens with orchestrator parsing protocol
+- [x] Evidence-gated verification with banned phrases and auto-downgrade
+- [x] Plan granularity constraint (2-5 min tasks with file path, code block, verify command)
+- [x] Strategy abstraction (PDCA cyclic, pipeline linear, auto-selection)
+- [x] Experimental status and interdisciplinary framing in README
+
 ### v0.6.0 (2026-04-04)
 - [x] Expanded attention-filters skill (prompt templates, token budgets, cycle-back filtering, verification checklist)
 - [x] Explorer skip heuristic in plan-phase skill
@@ -74,6 +82,7 @@
 
 | Date | Version | Changes |
 |------|---------|---------|
+| 2026-04-04 | v0.7.0 | Process rigor: context isolation, status tokens, evidence-gated verification, plan granularity, strategy abstraction |
 | 2026-04-04 | v0.6.0 | Quality/polish: expanded attention filters, Explorer skip heuristic, agent persona normalization, quickstart example |
 | 2026-04-04 | v0.5.0 | Robustness: lib validation, hook points, phase rollback, per-workflow models, regression detection, parallel reviewers |
 | 2026-04-04 | v0.4.0 | Confidence gates, mini-Explorer, worktree merge flow, rollback script, test-first gate, memory audit |

docs/status.md

@@ -29,22 +29,32 @@ Three ArcheFlow PDCA cycles in one session, each using ArcheFlow's own orchestra
 - Runnable quickstart example (`examples/runnable-quickstart.md`)
 - CHANGELOG completed with missing v0.4.0 entry + roadmap version history
 
+### v0.7.0 — Superpowers-Inspired + Strategy Abstraction (8 commits, 485 lines, 20 files)
+- Context isolation protocol (attention-filters + all 7 agents)
+- Structured status tokens: DONE/DONE_WITH_CONCERNS/NEEDS_CONTEXT/BLOCKED
+- Evidence-gated verification: banned phrases, evidence markers, downgrade-to-INFO
+- Plan granularity constraint: 2-5 min tasks with file:line + code block + verify
+- Strategy abstraction: `pdca` (cyclic) vs `pipeline` (linear) vs `auto` (selected by task)
+- README: experimental status + interdisciplinary framing (psychology + process eng + software eng)
+- Review fixes: fast→pipeline auto-select, merge guard, evidence check completeness
+
 ### Key numbers
-| Metric | v0.3 → v0.6 delta |
+| Metric | v0.3 → v0.7 delta |
 |--------|-------------------|
-| Commits this session | 21 |
+| Commits this session | 29 |
-| Lines added | ~1,277 |
+| Lines added | ~1,762 |
-| Files touched | 25+ |
+| Files touched | 30+ |
 | Lib scripts | 8 → 9 (archeflow-rollback.sh) |
-| Skills | 24 (all now fleshed out) |
+| Skills | 24 (all fleshed out, no stubs remain) |
-| Review cycles | 3 (Guardian + Skeptic + Sage per round) |
+| Review cycles | 4 (v0.4: full, v0.5: full, v0.6: fast, v0.7: Guardian-only) |
-| Review findings fixed | 11 |
+| Review findings fixed | 15 |
 
 ### What to do next
-1. **End-to-end dogfood** — run `af-run` on a real task (not ArcheFlow itself) to test the full PDCA loop
+1. **End-to-end dogfood** — run `af-run` on a real task (not ArcheFlow itself) to test both strategies
-2. **Hook execution runtime** — the config documents 6 hook events but no runner yet
+2. **Hook execution runtime** — config documents 6 hook events but no runner yet
-3. **Publish** — consider tagging v0.6.0 and announcing on git.xorwell.de
+3. **Pipeline strategy testing** — exercise the `--strategy pipeline` path on a bug fix
-4. **GitHub Action** — automated PR review (roadmap item, low effort)
+4. **Publish** — tag v0.7.0, consider claude.com/plugins marketplace listing
+5. **GitHub Action** — automated PR review (roadmap item, low effort)
 
 ## 2026-04-03: Major Feature Sprint (v0.1 → v0.3)
 

lib/archeflow-review.sh

@@ -0,0 +1,197 @@
+#!/usr/bin/env bash
+# archeflow-review.sh — Get a git diff for Guardian review, with stats.
+#
+# Standalone diff helper for af-review. No PDCA orchestration — just extracts
+# the right diff and reports stats so the Claude Code agent can feed it to
+# Guardian (or other reviewers).
+#
+# Usage:
+#   archeflow-review.sh                          # Uncommitted changes (staged + unstaged)
+#   archeflow-review.sh --branch feat/batch-api  # Branch diff vs main
+#   archeflow-review.sh --commit HEAD~3..HEAD    # Commit range
+#   archeflow-review.sh --base develop           # Override base branch (default: main)
+#   archeflow-review.sh --stat-only              # Only print stats, no diff output
+#
+# Output:
+#   Prints the diff to stdout. Stats go to stderr so they don't pollute the diff.
+#   Exit code 0 if diff is non-empty, 1 if empty (nothing to review).
+
+set -euo pipefail
+
+# ---------------------------------------------------------------------------
+# Globals
+# ---------------------------------------------------------------------------
+
+BASE_BRANCH="main"
+MODE="uncommitted"   # uncommitted | branch | commit
+TARGET=""
+STAT_ONLY="false"
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+die() {
+  echo "[af-review] ERROR: $*" >&2
+  exit 1
+}
+
+info() {
+  echo "[af-review] $*" >&2
+}
+
+# Print diff stats (files changed, insertions, deletions) to stderr.
+print_stats() {
+  local diff_text="$1"
+
+  local files_changed lines_added lines_removed total_lines
+  files_changed=$(echo "$diff_text" | grep -c '^diff --git' || true)
+  lines_added=$(echo "$diff_text" | grep -c '^+[^+]' || true)
+  lines_removed=$(echo "$diff_text" | grep -c '^-[^-]' || true)
+  total_lines=$(echo "$diff_text" | wc -l | tr -d ' ')
+
+  info "--- Review Stats ---"
+  info "Files changed:  ${files_changed}"
+  info "Lines added:    +${lines_added}"
+  info "Lines removed:  -${lines_removed}"
+  info "Diff size:      ${total_lines} lines"
+
+  if [[ "$total_lines" -gt 500 ]]; then
+    info "Warning: large diff (>500 lines). Consider reviewing per-file."
+  fi
+}
+
+# Detect the default base branch (main or master).
+detect_base_branch() {
+  if git show-ref --verify --quiet "refs/heads/main" 2>/dev/null; then
+    echo "main"
+  elif git show-ref --verify --quiet "refs/heads/master" 2>/dev/null; then
+    echo "master"
+  else
+    echo "main"
+  fi
+}
+
+# ---------------------------------------------------------------------------
+# Argument parsing
+# ---------------------------------------------------------------------------
+
+parse_args() {
+  while [[ $# -gt 0 ]]; do
+    case "$1" in
+      --branch)
+        MODE="branch"
+        TARGET="${2:?Missing branch name after --branch}"
+        shift 2
+        ;;
+      --commit)
+        MODE="commit"
+        TARGET="${2:?Missing commit range after --commit}"
+        shift 2
+        ;;
+      --base)
+        BASE_BRANCH="${2:?Missing base branch after --base}"
+        shift 2
+        ;;
+      --stat-only)
+        STAT_ONLY="true"
+        shift
+        ;;
+      -h|--help)
+        echo "Usage: $0 [--branch <name>] [--commit <range>] [--base <branch>] [--stat-only]"
+        echo ""
+        echo "  (no args)           Review uncommitted changes (staged + unstaged)"
+        echo "  --branch <name>     Review branch diff against base (default: main)"
+        echo "  --commit <range>    Review a commit range (e.g. HEAD~3..HEAD)"
+        echo "  --base <branch>     Override base branch (default: auto-detect main/master)"
+        echo "  --stat-only         Print stats only, no diff output"
+        exit 0
+        ;;
+      *)
+        die "Unknown argument: $1. Use --help for usage."
+        ;;
+    esac
+  done
+}
+
+# ---------------------------------------------------------------------------
+# Diff extraction
+# ---------------------------------------------------------------------------
+
+get_diff() {
+  local diff_text=""
+
+  case "$MODE" in
+    uncommitted)
+      # Combine staged and unstaged changes against HEAD
+      diff_text=$(git diff HEAD 2>/dev/null || true)
+      if [[ -z "$diff_text" ]]; then
+        # Maybe everything is staged, try just staged
+        diff_text=$(git diff --cached 2>/dev/null || true)
+      fi
+      ;;
+    branch)
+      # Verify target branch exists
+      if ! git show-ref --verify --quiet "refs/heads/${TARGET}" 2>/dev/null; then
+        # Maybe it's a remote branch
+        if ! git rev-parse --verify "${TARGET}" &>/dev/null; then
+          die "Branch '${TARGET}' not found."
+        fi
+      fi
+      diff_text=$(git diff "${BASE_BRANCH}...${TARGET}" 2>/dev/null || true)
+      ;;
+    commit)
+      # Validate commit range resolves
+      if ! git rev-parse "${TARGET}" &>/dev/null 2>&1; then
+        die "Invalid commit range: '${TARGET}'"
+      fi
+      diff_text=$(git diff "${TARGET}" 2>/dev/null || true)
+      ;;
+  esac
+
+  echo "$diff_text"
+}
+
+# ---------------------------------------------------------------------------
+# Main
+# ---------------------------------------------------------------------------
+
+main() {
+  # Verify we're in a git repo
+  if ! git rev-parse --is-inside-work-tree &>/dev/null; then
+    die "Not inside a git repository."
+  fi
+
+  parse_args "$@"
+
+  # Auto-detect base branch if not overridden
+  if [[ "$BASE_BRANCH" == "main" ]]; then
+    BASE_BRANCH=$(detect_base_branch)
+  fi
+
+  # Describe what we're reviewing
+  case "$MODE" in
+    uncommitted) info "Reviewing: uncommitted changes vs HEAD" ;;
+    branch)      info "Reviewing: branch '${TARGET}' vs '${BASE_BRANCH}'" ;;
+    commit)      info "Reviewing: commit range '${TARGET}'" ;;
+  esac
+
+  local diff_text
+  diff_text=$(get_diff)
+
+  # Validate non-empty
+  if [[ -z "$diff_text" ]]; then
+    info "No changes found. Nothing to review."
+    exit 1
+  fi
+
+  # Print stats to stderr
+  print_stats "$diff_text"
+
+  # Output the diff to stdout (unless stat-only)
+  if [[ "$STAT_ONLY" != "true" ]]; then
+    echo "$diff_text"
+  fi
+}
+
+main "$@"

skills/attention-filters/SKILL.md

@@ -1,109 +0,0 @@
----
-name: attention-filters
-description: Use when spawning archetype agents to decide what context each agent receives. Reduces token waste and sharpens focus by passing only relevant artifacts.
----
-
-# Attention Filters
-
-Each archetype needs different context. Pass only what's relevant — not everything.
-
-| Archetype | Receives | Does NOT Receive |
-|-----------|----------|-----------------|
-| Explorer | Task description, codebase access | Prior proposals or reviews |
-| Creator | Explorer's research + task description | Implementation details |
-| Maker | Creator's proposal | Explorer's research, reviews |
-| Guardian | Maker's git diff + proposal risk section | Explorer's research |
-| Skeptic | Creator's proposal (focus: assumptions) | Git diff details |
-| Trickster | Maker's git diff only | Everything else |
-| Sage | Proposal + implementation + diff | Explorer's raw research |
-
-## Why This Matters
-
-- **Token cost:** A Guardian reading the Explorer's 2000-word research wastes ~2600 tokens on irrelevant context
-- **Focus:** An agent with too much context drifts from its archetype's concern
-- **Shadow prevention:** Over-loading context encourages rabbit-holing (Explorer) and scope creep (Maker)
-
-## In Practice
-
-When spawning a Check-phase agent, include only the filtered context in the prompt:
-
-```
-# Guardian receives:
-"Review these changes: <git diff output>
-The proposal identified these risks: <risks section only>
-Verdict: APPROVED or REJECTED with findings."
-
-# NOT:
-"Here is the full research, the full proposal, the full implementation,
-the full git log, and everything else we have..."
-```
-
-## Prompt Construction Templates
-
-### Explorer
-- **Receives:** Task description, file tree (max 200 lines), prior-cycle feedback (if cycle 2+)
-- **Excludes:** Creator proposals, Maker diffs, reviewer outputs
-- **Token target:** ~2000 tokens input
-
-### Creator
-- **Receives:** Task description, Explorer research (if available), prior-cycle feedback (if cycle 2+)
-- **Excludes:** Maker diffs, reviewer outputs
-- **Token target:** ~3000 tokens input
-
-### Maker
-- **Receives:** Creator's proposal (full), test strategy section, file list
-- **Excludes:** Explorer research, reviewer outputs, prior-cycle feedback
-- **Token target:** ~2500 tokens input
-
-### Guardian
-- **Receives:** Maker's git diff, proposal risk section, test results
-- **Excludes:** Explorer research, Creator rationale, Skeptic/Sage outputs
-- **Token target:** ~2000 tokens input
-
-### Skeptic
-- **Receives:** Creator's proposal (assumptions + architecture decision), confidence scores
-- **Excludes:** Git diff details, Explorer raw research, other reviewer outputs
-- **Token target:** ~1500 tokens input
-
-### Trickster
-- **Receives:** Maker's git diff only, attack surface summary (file types + entry points)
-- **Excludes:** Proposal, research, other reviewer outputs
-- **Token target:** ~1500 tokens input
-
-### Sage
-- **Receives:** Creator's proposal, Maker's implementation summary + diff, test results
-- **Excludes:** Explorer raw research, other reviewer verdicts
-- **Token target:** ~2500 tokens input
-
-## Token Budget Targets
-
-| Archetype | Fast | Standard | Thorough |
-|-----------|------|----------|----------|
-| Explorer  | skip | 2000     | 3000     |
-| Creator   | 2000 | 3000     | 4000     |
-| Maker     | 2000 | 2500     | 3000     |
-| Guardian  | 1500 | 2000     | 2500     |
-| Skeptic   | skip | 1500     | 2000     |
-| Trickster | skip | skip     | 1500     |
-| Sage      | skip | 2500     | 3000     |
-
-"skip" means the archetype is not spawned in that workflow tier.
-
-## Cycle-Back Filtering
-
-When injecting prior-cycle feedback into cycle 2+:
-
-1. **Summary only** — pass the structured feedback table (issue, source, severity), not full reviewer artifacts
-2. **Strip resolved items** — if a finding was marked Fixed in the Act phase, exclude it
-3. **Compress context** — prior proposal diffs reduce to "What Changed" section only (not full re-proposal)
-4. **Cap at 500 tokens** — if feedback exceeds this, summarize by severity (CRITICAL first, then WARNING, drop INFO)
-
-## Filter Verification Checklist
-
-Before spawning each agent, verify:
-
-- [ ] Prompt contains ONLY the artifacts listed in that archetype's "Receives" above
-- [ ] No cross-contamination from other reviewers' outputs
-- [ ] Token count is within 20% of the target for the current workflow tier
-- [ ] Prior-cycle feedback (if any) is summarized, not raw
-- [ ] Excluded artifacts are genuinely absent (search for keywords like file paths from excluded sources)

skills/check-phase/SKILL.md

@@ -1,187 +1,110 @@
 ---
 name: check-phase
-description: Use when you are acting as Guardian, Skeptic, Sage, or Trickster archetype in the Check phase. Defines shared review rules and output format.
+description: Use when acting as Guardian, Skeptic, Sage, or Trickster in the Check phase. Defines review rules, finding format, attention filters, and spawning protocol.
 ---
 
 # Check Phase
 
-Multiple reviewers examine the Maker's implementation in parallel. Each agent definition has its specific protocol — this skill defines the shared rules.
+Reviewers examine the Maker's implementation. This skill defines shared rules, finding format, and spawning protocol.
 
 ## Shared Rules
 
-1. **Read the proposal first.** Review against the intended design, not invented requirements.
+1. Review against the proposal's intended design, not invented requirements.
-2. **Read the actual code.** Use `git diff` on the Maker's branch. Don't review descriptions alone.
+2. Read actual code via `git diff` on the Maker's branch.
-3. **Structured findings.** Use the standardized finding format below for every issue.
+3. Use the finding format below for every issue.
-4. **Clear verdict:** `APPROVED` or `REJECTED` with rationale.
+4. Give a clear verdict: `APPROVED` or `REJECTED` with rationale.
+5. `STATUS: DONE` signals agent completion. `APPROVED`/`REJECTED` is domain output. Both are parsed independently.
 
 ## Finding Format
 
-Every finding must use this format for cross-cycle tracking:
-
-```
 | Location | Severity | Category | Description | Fix |
 |----------|----------|----------|-------------|-----|
-| src/auth/handler.ts:48 | CRITICAL | security | Empty string bypasses validation | Add length check before processing |
+| src/auth/handler.ts:48 | CRITICAL | security | Empty string bypasses validation | Add length check |
-```
 
-**Severity:**
+**Severity:** CRITICAL = must fix, blocks approval. WARNING = should fix, doesn't block alone. INFO = nice to have, never blocks.
-- **CRITICAL** — Must fix. Blocks approval.
-- **WARNING** — Should fix. Doesn't block alone.
-- **INFO** — Nice to have. Never blocks.
 
-**Categories** (use consistently for cross-cycle tracking):
+**Categories:** `security` `reliability` `design` `breaking-change` `dependency` `quality` `testing` `consistency`
-- `security` — Injection, auth bypass, data exposure, secrets
-- `reliability` — Error handling, edge cases, race conditions, crashes
-- `design` — Architecture, assumptions, scalability, coupling
-- `breaking-change` — API compatibility, schema migrations, removals
-- `dependency` — New deps, version conflicts, license issues
-- `quality` — Readability, maintainability, naming, duplication
-- `testing` — Missing tests, weak assertions, untested paths
-- `consistency` — Deviates from codebase patterns
 
-## Consolidated Output
+## Evidence Requirements
 
-After all reviewers finish, compile:
+Every CRITICAL or WARNING must include concrete evidence. Without evidence, downgrade to INFO.
 
-```markdown
+**Valid evidence:** command output, exit codes, code citations with line numbers, git diff excerpts, reproduction steps.
-## Check Phase Results — Cycle N
 
-### Guardian: APPROVED
+**Banned in CRITICAL/WARNING:** "might be", "could potentially", "appears to", "seems like", "may not". Rewrite with evidence or downgrade.
-| Location | Severity | Category | Description | Fix |
-|----------|----------|----------|-------------|-----|
-| src/auth/handler.ts:52 | WARNING | security | Missing rate limit | Add rate limiter middleware |
 
-### Skeptic: APPROVED
+For each CRITICAL/WARNING, state: (1) what was tested, (2) what was observed, (3) what correct behavior should be.
-| Location | Severity | Category | Description | Fix |
-|----------|----------|----------|-------------|-----|
-| src/auth/handler.ts:30 | INFO | design | Consider caching validated tokens | Add TTL cache for token validation |
 
-### Sage: APPROVED
+## Attention Filters
-| Location | Severity | Category | Description | Fix |
-|----------|----------|----------|-------------|-----|
-| tests/auth.test.ts:15 | WARNING | testing | Test names don't describe behavior | Rename to "should reject expired tokens" |
 
-### Trickster: REJECTED
+Each archetype receives only relevant context. Do not pass everything.
-| Location | Severity | Category | Description | Fix |
-|----------|----------|----------|-------------|-----|
-| src/auth/handler.ts:48 | CRITICAL | reliability | Empty string bypasses validation | Add `if (!token || token.trim() === '')` guard |
 
-### Deduplication
+| Archetype | Receives | Excludes |
-If two reviewers raise the same issue (same file + same category), merge:
+|-----------|----------|----------|
-| Guardian + Skeptic | CRITICAL | security | Input not sanitized (src/api.ts:30) | Add validation |
+| Guardian | Maker's git diff + proposal risk section + test results | Explorer research, Creator rationale, other reviewers |
+| Skeptic | Creator's proposal (assumptions + architecture) + confidence scores | Git diff, Explorer research, other reviewers |
+| Sage | Creator's proposal + Maker's diff + implementation summary + test results | Explorer raw research, other reviewer verdicts |
+| Trickster | Maker's git diff + attack surface summary (file types + entry points) | Proposal, research, other reviewers |
 
-Use the higher severity. Don't double-count in the verdict.
+**Token budget targets:**
 
-### Verdict: REJECTED — 1 critical finding
+| Archetype | Fast | Standard | Thorough |
-→ Build cycle feedback (see orchestration skill) and feed to Plan phase
+|-----------|------|----------|----------|
-```
+| Guardian | 1500 | 2000 | 2500 |
+| Skeptic | skip | 1500 | 2000 |
+| Trickster | skip | skip | 1500 |
+| Sage | skip | 2500 | 3000 |
+
+**Context isolation:** Agents receive fresh, controller-constructed context only. No session bleed, no cross-agent contamination, no ambient knowledge. Verify zero references to excluded artifacts before spawning.
+
+**Cycle-back filtering (cycle 2+):** Pass structured feedback table only (not full reviewer artifacts). Strip resolved items. Cap at 500 tokens — summarize by severity if exceeded.
 
 ## Reviewer Spawning Protocol
 
-This section defines the exact sequence for spawning reviewers in the Check phase.
-
 ### Step 1: Guardian First (mandatory)
 
-Guardian always runs first, before any other reviewer. It receives the Maker's git diff and the proposal's risk section only.
+Guardian always runs first. It receives the Maker's git diff and the proposal's risk section only.
-
-**Context for Guardian:**
-- `git diff main...<maker-branch>` (the actual code changes)
-- Risk section from `plan-creator.md` (if present)
-- Do NOT include: Explorer research, full proposal, other reviewer outputs
-
-```
-Agent(
-  description: "Guardian: security and risk review for <task>",
-  prompt: "You are the GUARDIAN archetype.
-    Review the diff: <maker's diff>
-    Proposal risks: <risk section from plan-creator.md>
-    Assess: security vulnerabilities, reliability risks, breaking changes, dependency risks.
-    Output: APPROVED or REJECTED with findings in the standardized format.
-    Each finding: | Location | Severity | Category | Description | Fix |",
-  model: <resolve_model guardian $WORKFLOW>
-)
-```
 
 Save output to `.archeflow/artifacts/${RUN_ID}/check-guardian.md`.
 
 ### Step 2: A2 Fast-Path Evaluation
 
-After Guardian completes, parse its output before spawning other reviewers:
+After Guardian completes, count CRITICAL and WARNING findings in its output. If both are zero, and not escalated, and not first cycle of a thorough workflow — skip remaining reviewers and proceed to Act phase.
 
-```bash
+### Step 3: Parallel Remaining Reviewers
-CRITICAL_COUNT=$(grep -c "| CRITICAL |" ".archeflow/artifacts/${RUN_ID}/check-guardian.md" || echo 0)
-WARNING_COUNT=$(grep -c "| WARNING |" ".archeflow/artifacts/${RUN_ID}/check-guardian.md" || echo 0)
 
-# A2 fast-path: skip remaining reviewers if Guardian is clean
+If A2 does not trigger, spawn remaining reviewers in parallel:
-# Exception: first cycle of thorough workflows always spawns all reviewers
-if [[ "$CRITICAL_COUNT" -eq 0 && "$WARNING_COUNT" -eq 0 \
-      && "$ESCALATED" != "true" \
-      && ! ("$WORKFLOW" == "thorough" && "$CYCLE" -eq 1) ]]; then
-  echo "Guardian fast-path: 0 CRITICAL, 0 WARNING — skipping remaining reviewers."
-  # Proceed directly to Act phase
-fi
-```
-
-### Step 3: Parallel Reviewer Spawning
-
-If A2 does not trigger, spawn remaining reviewers in parallel based on workflow:
 
 | Workflow | Reviewers (after Guardian) |
 |----------|--------------------------|
 | `fast` | None (Guardian only) |
-| `fast` (escalated via A1) | Skeptic + Sage |
+| `fast` (escalated) | Skeptic + Sage |
 | `standard` | Skeptic + Sage |
 | `thorough` | Skeptic + Sage + Trickster |
 
-Spawn all applicable reviewers in a single message with multiple Agent calls:
+Each reviewer gets context per the attention filters above.
 
-```
+### Step 4: Collect and Consolidate
-# Standard workflow example — spawn Skeptic and Sage in parallel:
-Agent(
-  description: "Skeptic: challenge assumptions for <task>",
-  prompt: "<Skeptic prompt with Creator's proposal>",
-  model: <resolve_model skeptic $WORKFLOW>
-)
 
-Agent(
+For each reviewer: save to `.archeflow/artifacts/${RUN_ID}/check-<archetype>.md`, emit `review.verdict` event, record sequence number.
-  description: "Sage: holistic quality review for <task>",
+
-  prompt: "<Sage prompt with proposal + diff + implementation summary>",
+**Deduplication:** If two reviewers raise the same issue (same file + same category), merge into one finding using the higher severity. Don't double-count.
-  model: <resolve_model sage $WORKFLOW>
+
-)
+**Verdict:** Count CRITICAL findings across all reviewers (after dedup). Any CRITICAL = `REJECTED`. Otherwise `APPROVED`.
+
+Example consolidated output:
+
+```markdown
+## Check Phase Results — Cycle 1
+### Guardian: APPROVED
+| Location | Severity | Category | Description | Fix |
+|----------|----------|----------|-------------|-----|
+| src/auth.ts:52 | WARNING | security | Missing rate limit | Add rate limiter |
+### Verdict: APPROVED — 0 critical, 1 warning
 ```
 
-Each reviewer gets context per the attention filters defined in `archeflow:orchestration`:
+## Timeout Handling
-- **Skeptic:** Creator's proposal (assumptions section focus)
-- **Sage:** Creator's proposal + Maker's diff + implementation summary
-- **Trickster:** Maker's diff only
 
-### Step 4: Collect Results
+Each reviewer has a **5-minute timeout**. On timeout: emit `agent.complete` with `"error": true`, log WARNING, treat as no findings, proceed.
 
-Wait for all spawned reviewers to return. For each:
+**Exception:** Guardian timeout is blocking — abort Check phase and report to user.
-1. Save output to `.archeflow/artifacts/${RUN_ID}/check-<archetype>.md`
-2. Emit `review.verdict` event with findings
-3. Record sequence number for DAG parent tracking
-
-### Timeout Handling
-
-Each reviewer has a **5-minute timeout**. If a reviewer does not return within 5 minutes:
-1. Emit `agent.complete` with `"error": true, "reason": "timeout"`
-2. Log a WARNING — do not block the run
-3. Treat the timed-out reviewer as having delivered no findings (neither approved nor rejected)
-4. Proceed with available verdicts
-
-If Guardian times out, this is a blocking failure — abort the Check phase and report to the user.
-
-### Re-Check Protocol (Act Phase Fixes)
-
-When the Act phase routes findings back to the Maker and the Maker applies fixes in a subsequent cycle, the Check phase re-runs with the updated diff. Reviewers who previously rejected should focus on whether their specific findings were addressed. The structured feedback from `act-feedback.md` provides the mapping of which findings were routed where.
-
----
-
-## Why Structured Findings Matter
-
-The standardized format enables:
-- **Cross-cycle tracking:** Same category + location = same issue. Can detect resolution or regression.
-- **Feedback routing:** Security/design findings → Creator. Quality/testing findings → Maker.
-- **Shadow detection:** CRITICAL:WARNING ratios, finding counts, and category distributions are measurable.
-- **Metrics:** Severity counts feed into the orchestration summary.

skills/colette-bridge/SKILL.md

@@ -186,7 +186,7 @@ When regenerating:
 
 ## Per-Agent Attention Filters
 
-Not every agent needs the full bundle. The bridge defines attention filters that control which sections each archetype receives. This extends the base attention filters from `archeflow:attention-filters`.
+Not every agent needs the full bundle. The bridge defines attention filters that control which sections each archetype receives. This extends the base attention filters from `archeflow:check-phase`.
 
 | Archetype | Bundle sections injected | Rationale |
 |-----------|------------------------|-----------|

skills/orchestration/SKILL.md

@@ -7,6 +7,58 @@ description: Use when executing a multi-agent orchestration — spawning archety
 
 This skill guides you through running a full ArcheFlow orchestration using Claude Code's native Agent tool and git worktrees.
 
+## Strategy Selection
+
+A **strategy** defines the shape of an orchestration run — which phases execute, in what order, and when to iterate. A **workflow** (fast/standard/thorough) controls the depth within a strategy.
+
+### Available Strategies
+
+| Strategy | Flow | When to Use |
+|----------|------|-------------|
+| `pdca` | Plan -> Do -> Check -> Act (cyclic) | Refactors, thorough reviews, multi-concern tasks |
+| `pipeline` | Plan -> Implement -> Spec-Review -> Quality-Review -> Verify (linear) | Bug fixes, fast patches, single-concern tasks |
+| `auto` | Selected by task analysis | Default — let ArcheFlow decide |
+
+### Strategy Interface
+
+Every strategy defines:
+
+- **Phases** — ordered list of execution stages
+- **Agent mapping** — which archetypes run in each phase
+- **Transition rules** — conditions for moving between phases
+- **Iteration model** — cyclic (PDCA) or linear (pipeline)
+- **Exit conditions** — when the run terminates
+
+### PDCA Strategy
+
+The existing orchestration flow (Steps 0-4 below). Cyclic — the Act phase can feed back to Plan for another iteration. Best for tasks requiring multiple review perspectives and iterative refinement.
+
+### Pipeline Strategy
+
+Linear flow with no cycle-back. Faster for well-understood tasks where one pass is sufficient.
+
+| Phase | Agent | Purpose |
+|-------|-------|---------|
+| Plan | Creator | Design proposal |
+| Implement | Maker | Build in worktree |
+| Spec-Review | Guardian, then Skeptic | Security + assumption check (sequential) |
+| Quality-Review | Sage | Code quality review |
+| Verify | (automated) | Run tests, apply targeted fix if CRITICAL |
+
+No cycle-back — WARNINGs are logged but do not block. CRITICALs in Verify trigger a single targeted fix attempt by the Maker, not a full cycle.
+
+### Auto-Selection Rules
+
+When `strategy: auto` (default):
+
+- Task contains "fix", "bug", "patch", "hotfix" → `pipeline`
+- Task contains "refactor", "redesign", "review" → `pdca`
+- Workflow is `thorough` → `pdca` (always)
+- Workflow is `fast` with single file → `pipeline`
+- Otherwise → `pdca`
+
+---
+
 ## Step 0: Choose a Workflow
 
 If `.archeflow/teams/<name>.yaml` exists, the user can reference a team preset: `"Use the backend team"`. Load the preset's phase config instead of built-in defaults. See `archeflow:custom-archetypes` skill for preset format.

skills/plan-phase/SKILL.md

@@ -118,6 +118,46 @@ When the Creator receives structured feedback from a prior cycle, the proposal m
 
 CRITICAL findings cannot be deferred or disputed — they must be fixed or the proposal will be rejected again.
 
+## Task Granularity
+
+Each change item in the Creator's proposal must be a **2-5 minute task** — specific enough that the Maker can implement it without interpretation.
+
+### Requirements per Change Item
+
+Every item in the `### Changes` section must include:
+
+1. **Exact file path** — `src/auth/handler.ts`, not "the auth module"
+2. **What to change** — a code block showing the target state or transformation
+3. **How to verify** — a command or check that confirms correctness
+
+### Good Example
+
+```markdown
+1. **`src/auth/handler.ts:48`** — Add input length validation before token processing
+   ```typescript
+   if (!token || token.trim().length === 0) {
+     throw new ValidationError('Token must not be empty');
+   }
+   ```
+   **Verify:** `npm test -- --grep "empty token"` passes
+```
+
+### Bad Example
+
+```markdown
+1. **Auth module** — Fix the validation logic
+```
+
+This is too vague. Which file? Which function? What does "fix" mean? The Maker will guess.
+
+### Granularity Check
+
+- If a single change item would take **>5 minutes**, split it into smaller items
+- If a non-trivial task has **<2 change items**, it is under-specified — the Creator missed something
+- Each item should touch **1-2 files** at most. Cross-cutting changes need separate items per file.
+
+---
+
 ## Explorer Skip Conditions
 
 Not every task needs Explorer research. Use this decision table:

skills/presence/SKILL.md

@@ -89,12 +89,12 @@ Only show if the user explicitly asks or if `progress.dag_on_complete: true` in
 When ArcheFlow activates at session start (via the `using-archeflow` skill), show ONE line:
 
 ```
-archeflow v0.6.0 · 24 skills · writing domain detected
+archeflow v0.7.0 · 24 skills · writing domain detected
 ```
 
 Or for code projects:
 ```
-archeflow v0.6.0 · 24 skills · code domain
+archeflow v0.7.0 · 24 skills · code domain
 ```
 
 If ArcheFlow decides NOT to activate (simple task, single file):

skills/review/SKILL.md

@@ -0,0 +1,146 @@
+---
+name: review
+description: |
+  Review-only mode. Run Guardian + optional reviewers on an existing diff or branch,
+  without any Plan/Do orchestration. The highest-ROI mode for catching design-level bugs.
+  <example>User: "af-review"</example>
+  <example>User: "Review the last commit"</example>
+  <example>User: "af-review --reviewers guardian,skeptic"</example>
+---
+
+# ArcheFlow Review Mode
+
+Run reviewers on existing code changes without orchestrating implementation.
+This is the most cost-effective mode — it delivers Guardian's error-path analysis
+without the Maker overhead.
+
+## When to Use
+
+- After you've implemented something and want a quality check
+- On a PR or branch before merging
+- When the sprint runner flags a task as DONE_WITH_CONCERNS
+- As a pre-commit quality gate for complex changes
+
+## Invocation
+
+```
+af-review                                    # Review uncommitted changes
+af-review --branch feat/batch-api            # Review branch diff against main
+af-review --commit HEAD~3..HEAD              # Review last 3 commits
+af-review --reviewers guardian,skeptic,sage   # Choose reviewers (default: guardian)
+af-review --evidence                         # Enable evidence-gating (stricter)
+```
+
+---
+
+## Execution
+
+### Step 1: Get the Diff
+
+Use `lib/archeflow-review.sh` to extract the diff and stats:
+
+```bash
+# Uncommitted changes (default)
+DIFF=$(bash lib/archeflow-review.sh)
+
+# Branch diff against main
+DIFF=$(bash lib/archeflow-review.sh --branch feat/batch-api)
+
+# Commit range
+DIFF=$(bash lib/archeflow-review.sh --commit HEAD~3..HEAD)
+
+# Override base branch
+DIFF=$(bash lib/archeflow-review.sh --branch feat/x --base develop)
+
+# Stats only (no diff output)
+bash lib/archeflow-review.sh --stat-only
+```
+
+The script prints the diff to stdout and stats to stderr. It exits 1 if the diff
+is empty (nothing to review). For large diffs (>500 lines), it warns on stderr.
+
+### Step 2: Spawn Reviewers
+
+Default: Guardian only (fastest, highest ROI).
+With `--reviewers`: spawn requested reviewers in parallel.
+
+**Guardian** (always first):
+```
+Agent(
+  description: "Guardian: review changes for <project>",
+  prompt: "You are the GUARDIAN archetype — security and risk reviewer.
+
+    Review this diff for: security vulnerabilities, error handling gaps,
+    data loss scenarios, race conditions, and breaking changes.
+
+    For each finding: cite specific code (file:line), state what you tested
+    or observed, state what the correct behavior should be.
+
+    Diff:
+    <DIFF>
+
+    STATUS: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED",
+  subagent_type: "code-reviewer"
+)
+```
+
+**Skeptic** (if requested):
+- Focus: hidden assumptions, edge cases, scalability
+- Context: diff + any design docs
+
+**Sage** (if requested):
+- Focus: code quality, test coverage, maintainability
+- Context: diff + surrounding code
+
+**Trickster** (if requested):
+- Focus: adversarial inputs, failure injection, chaos testing
+- Context: diff only
+
+### Step 3: Collect and Report
+
+Parse each reviewer's output. Show findings:
+
+```
+── af-review: <project> ───────────────────────
+Reviewers: guardian, skeptic
+
+🛡️ Guardian: 2 findings (1 HIGH, 1 MEDIUM)
+  [HIGH] Timeout marks variant as done — loses batch state (fanout.py:552)
+  [MEDIUM] No JSON error handling on corrupted state (batch.py:310)
+
+🤔 Skeptic: 1 finding (1 INFO)
+  [INFO] hash() non-deterministic across processes (fanout.py:524)
+
+Total: 3 findings (1 HIGH, 1 MEDIUM, 1 INFO)
+────────────────────────────────────────────────
+```
+
+### Step 4: Evidence Gate (if --evidence)
+
+When `--evidence` is active, apply the evidence requirements from `archeflow:check-phase`:
+- Scan findings for banned phrases ("might be", "could potentially", etc.)
+- Check for evidence markers (exit codes, line numbers, reproduction steps)
+- Downgrade unsupported findings to INFO
+
+---
+
+## Integration with Sprint Runner
+
+The sprint runner can invoke `af-review` automatically:
+
+| Sprint trigger | Review action |
+|----------------|--------------|
+| Task marked DONE_WITH_CONCERNS | Run Guardian on the agent's changes |
+| Task is L/XL estimate | Run Guardian + Skeptic after completion |
+| Task involves security keywords | Run Guardian automatically |
+| User requests | Run specified reviewers |
+
+---
+
+## Cost
+
+Review-only is 60-80% cheaper than full PDCA:
+- No Explorer research (~30% of PDCA cost)
+- No Creator planning (~20% of PDCA cost)
+- No Maker implementation (already done)
+- Only reviewer token costs remain

skills/run/SKILL.md

@@ -63,7 +63,40 @@ After emitting `run.start`, record `SEQ_RUN_START=1`.
 
 If `--start-from` is specified, verify that the required prior artifacts exist in `.archeflow/artifacts/${RUN_ID}/` before skipping phases. If missing, abort with an error.
 
-#### 0a. Lib Script Validation
+#### 0a. Strategy Resolution
+
+Determine the execution strategy before proceeding. Strategy controls the overall flow shape (cyclic vs linear).
+
+```bash
+# Read strategy from config or CLI flag
+STRATEGY=$(grep '^strategy:' "$CONFIG" 2>/dev/null | sed 's/strategy:\s*//' | tr -d '"' | head -1)
+STRATEGY="${STRATEGY:-auto}"
+
+# CLI override: --strategy pdca|pipeline
+# (parsed from invocation args, overrides config)
+
+# Auto-select logic
+if [[ "$STRATEGY" == "auto" ]]; then
+  TASK_LOWER=$(echo "$TASK" | tr '[:upper:]' '[:lower:]')
+  if echo "$TASK_LOWER" | grep -qE '(fix|bug|patch|hotfix)'; then
+    STRATEGY="pipeline"
+  elif echo "$TASK_LOWER" | grep -qE '(refactor|redesign|review)'; then
+    STRATEGY="pdca"
+  elif [[ "$WORKFLOW" == "fast" ]]; then
+    STRATEGY="pipeline"
+  elif [[ "$WORKFLOW" == "thorough" ]]; then
+    STRATEGY="pdca"
+  else
+    STRATEGY="pdca"
+  fi
+fi
+
+echo "Strategy: $STRATEGY"
+```
+
+**Strategy dispatch:** If `STRATEGY=pdca`, execute Steps 1-5 below (existing PDCA flow). If `STRATEGY=pipeline`, skip to the "Pipeline Strategy Execution" section at the end of this skill.
+
+#### 0b. Lib Script Validation
 
 Verify that all required library scripts exist and are executable before proceeding. Fail fast if any dependency is missing.
 
@@ -102,7 +135,7 @@ if ! command -v jq &>/dev/null; then
 fi
 ```
 
-#### 0b. Memory Injection
+#### 0c. Memory Injection
 
 Load cross-run memory lessons and inject into agent prompts. Use `--audit` to track which lessons were injected for this run:
 
@@ -121,7 +154,7 @@ ${MEMORY_LESSONS}"
 fi
 ```
 
-#### 0c. Model Configuration
+#### 0d. Model Configuration
 
 Read model assignment from `.archeflow/config.yaml` and resolve the model for each archetype based on the current workflow. Per-workflow overrides take precedence over per-archetype overrides, which take precedence over the default.
 
@@ -166,6 +199,31 @@ Use `resolve_model` when spawning each agent to pass the correct model. The reso
 
 ---
 
+### Status Token Protocol
+
+Every agent ends its output with a `STATUS:` line. The orchestrator parses this to decide the next action.
+
+**Parsing:**
+
+```bash
+STATUS=$(tail -20 "$AGENT_OUTPUT" | grep -oE 'STATUS: (DONE|DONE_WITH_CONCERNS|NEEDS_CONTEXT|BLOCKED)' | head -1)
+STATUS="${STATUS#STATUS: }"
+if [[ -z "$STATUS" ]]; then STATUS="DONE"; fi
+```
+
+**Status to action mapping:**
+
+| Status | Action |
+|--------|--------|
+| `DONE` | Proceed to next phase or agent |
+| `DONE_WITH_CONCERNS` | Log concerns in event data, proceed |
+| `NEEDS_CONTEXT` | Pause run, request missing information from user |
+| `BLOCKED` | Abort phase, report blocker to user |
+
+Include the parsed status in the `agent.complete` event data: `"status":"<STATUS>"`.
+
+---
+
 ### 1. Plan Phase
 
 #### 1a. Explorer (if standard or thorough)
@@ -452,6 +510,61 @@ Spawn all applicable reviewers in parallel (multiple Agent calls in one message)
 
 After each returns, emit `review.verdict` and save artifact.
 
+#### 3c-ii. Evidence Validation
+
+After all reviewers complete, scan CRITICAL/WARNING findings for two conditions:
+1. **Banned phrases** — hedged language without evidence
+2. **Missing evidence** — no command output, code citation, or reproduction steps
+
+Downgrade unsupported findings to INFO before proceeding to Act.
+
+```bash
+BANNED_PHRASES=("might be" "could potentially" "appears to" "seems like" "may not")
+EVIDENCE_MARKERS=("exit" "output" "line [0-9]" ":[0-9]" "returned" "FAIL" "PASS" "assert")
+
+for artifact in .archeflow/artifacts/${RUN_ID}/check-*.md; do
+  REVIEWER=$(basename "$artifact" .md | sed 's/check-//')
+
+  # Read findings table rows (CRITICAL and WARNING only)
+  grep -E '\| (CRITICAL|WARNING) \|' "$artifact" 2>/dev/null | while IFS= read -r line; do
+    SEVERITY=$(echo "$line" | grep -oE '(CRITICAL|WARNING)' | head -1)
+    DOWNGRADE_REASON=""
+
+    # Check 1: banned phrases
+    for phrase in "${BANNED_PHRASES[@]}"; do
+      if echo "$line" | grep -qi "$phrase"; then
+        DOWNGRADE_REASON="banned phrase: $phrase"
+        break
+      fi
+    done
+
+    # Check 2: no evidence markers (only if not already flagged)
+    if [[ -z "$DOWNGRADE_REASON" ]]; then
+      HAS_EVIDENCE=false
+      for marker in "${EVIDENCE_MARKERS[@]}"; do
+        if echo "$line" | grep -qiE "$marker"; then
+          HAS_EVIDENCE=true
+          break
+        fi
+      done
+      if [[ "$HAS_EVIDENCE" == "false" ]]; then
+        DOWNGRADE_REASON="no evidence cited"
+      fi
+    fi
+
+    if [[ -n "$DOWNGRADE_REASON" ]]; then
+      echo "EVIDENCE DOWNGRADE: $REVIEWER $SEVERITY finding — $DOWNGRADE_REASON"
+      ./lib/archeflow-event.sh "$RUN_ID" decision check "" \
+        '{"what":"evidence_downgrade","from":"'"$SEVERITY"'","to":"INFO","reviewer":"'"$REVIEWER"'","reason":"'"$DOWNGRADE_REASON"'"}'
+      # Note: the orchestrator tracks downgraded findings separately —
+      # do not modify the artifact file (avoids sed corruption on table rows)
+    fi
+  done
+done
+```
+
+**Important:** Downgraded findings are tracked in events, NOT by modifying artifact files. The Act phase reads the decision events to know which findings were downgraded and excludes them from CRITICAL tallies.
+
 #### 3d. Phase Transition: Check to Act
 
 Collect all verdict seq numbers for the parent array.
@@ -689,3 +802,89 @@ Run ID: <run_id> | Workflow: <standard> | Cycle: 1/<max>
 Artifacts: .archeflow/artifacts/<run_id>/
 Report: .archeflow/events/<run_id>.jsonl
 ```
+
+---
+
+## Pipeline Strategy Execution
+
+When `STRATEGY=pipeline`, execute this linear flow instead of the PDCA cycle above.
+
+### Pipeline Phases
+
+```
+Plan -> Implement -> Spec-Review -> Quality-Review -> Verify
+```
+
+No cycle-back. Each phase runs once.
+
+### 1. Plan
+
+Spawn Creator only (no Explorer). Use fast-workflow Creator prompt with Mini-Reflect.
+
+Save output to `.archeflow/artifacts/${RUN_ID}/plan-creator.md`.
+
+### 2. Implement
+
+Spawn Maker in isolated worktree with Creator's proposal.
+
+Save output to `.archeflow/artifacts/${RUN_ID}/do-maker.md`.
+
+### 3. Spec-Review
+
+Run Guardian and Skeptic **sequentially** (Guardian first, then Skeptic only if Guardian has findings).
+
+- Guardian receives: Maker's git diff + proposal risk section
+- Skeptic receives: Creator's proposal (assumptions focus)
+
+Save to `check-guardian.md` and `check-skeptic.md`.
+
+### 4. Quality-Review
+
+Spawn Sage with proposal + diff + implementation summary.
+
+Save to `check-sage.md`.
+
+### 5. Verify
+
+Run the project's test suite. If tests pass and no CRITICAL findings exist:
+
+1. Merge the Maker's branch
+2. Emit `run.complete`
+
+If CRITICAL findings exist:
+
+1. **Do NOT merge yet** — the branch remains separate
+2. Spawn Maker for a **single targeted fix** — provide only the CRITICAL findings as context
+3. Re-run the reviewer(s) that raised the CRITICAL finding(s) on just the fixed files
+4. Re-run test suite
+5. If tests pass and re-review approves: merge
+6. If still failing after this one fix attempt: **abort** — do NOT merge, report to user with the branch name for manual resolution
+
+```bash
+# Pipeline verify: explicit merge guard
+if [[ "$VERIFY_PASS" == "true" ]]; then
+  ./lib/archeflow-git.sh merge "$RUN_ID" --no-ff
+  ./lib/archeflow-rollback.sh "$RUN_ID"  # post-merge test validation
+else
+  echo "Pipeline aborted: CRITICAL findings not resolved after 1 fix attempt."
+  echo "Branch: archeflow/$RUN_ID (not merged)"
+  # Emit run.complete with status: aborted
+fi
+```
+
+WARNINGs are logged in the run event but do not block the merge.
+
+### Pipeline Progress Display
+
+```
+━━━ ArcheFlow Pipeline: <task> ━━━━━━━━━━━━━━━━
+Run ID: <run_id> | Strategy: pipeline
+
+[Plan]     Creator designing...          -> done (20s)
+[Implement] Maker building...            -> done (60s, 3 files)
+[Spec]     Guardian reviewing...         -> APPROVED
+[Quality]  Sage reviewing...             -> APPROVED (1 WARNING)
+[Verify]   Tests passing...              -> merged to main
+
+━━━ Complete: 2m 15s ━━━━━━━━━━━━━━━━━━━━━━━━━━
+```

skills/sprint/SKILL.md

@@ -0,0 +1,302 @@
+---
+name: sprint
+description: |
+  Workspace sprint runner. Reads queue.json, spawns parallel agent teams across projects,
+  manages lifecycle (commit, push, next task), tracks progress. The main operational mode
+  for ArcheFlow in multi-project workspaces.
+  <example>User: "af-sprint"</example>
+  <example>User: "Run the sprint"</example>
+  <example>User: "af-sprint --slots 5 --dry-run"</example>
+---
+
+# Workspace Sprint Runner
+
+Read the task queue, spawn parallel agents across projects, collect results, commit+push,
+spawn next batch. Repeat until the queue is drained or budget is exhausted.
+
+## When to Use
+
+This is the **primary operational mode** for ArcheFlow in multi-project workspaces.
+Use it when the user says "run the sprint", "work the queue", "go autonomous", or
+invokes `af-sprint`.
+
+Do NOT use `archeflow:run` for individual tasks within a sprint — the sprint runner
+handles task dispatch internally, using `archeflow:run` only when a task warrants
+full PDCA orchestration.
+
+## Prerequisites
+
+- `docs/orchestra/queue.json` — task queue (managed by `./scripts/ws`)
+- `./scripts/ws` — workspace CLI for queue operations
+- Each project is a separate git repo under the workspace root
+
+## Invocation
+
+```
+af-sprint                          # Run sprint with defaults (4 slots, AUTONOM mode)
+af-sprint --slots 5                # Max 5 parallel agents
+af-sprint --dry-run                # Show what would run, don't execute
+af-sprint --priority P0,P1         # Only process P0 and P1 items
+af-sprint --project writing.colette # Only process items for this project
+```
+
+---
+
+## Execution Protocol
+
+### Step 0: Orient
+
+```bash
+# Load queue and workspace state
+QUEUE=$(cat docs/orchestra/queue.json)
+MODE=$(echo "$QUEUE" | jq -r '.mode')
+```
+
+Check mode:
+- `AUTONOM` → proceed without asking
+- `ATTENDED` → show plan, wait for user approval before each batch
+- `PAUSED` → report status only, do not start tasks
+
+Show one-line status:
+```
+sprint: AUTONOM · 7 pending (1×P0, 1×P2, 5×P3) · 4 slots
+```
+
+### Step 1: Select Batch
+
+Pick tasks for the next batch. Rules:
+
+1. **Priority cascade**: P0 first, then P1, then P2. Never start P3 unless user explicitly includes it.
+2. **Dependency check**: Skip tasks whose `depends_on` items aren't all `completed`.
+3. **One agent per project**: Never run two tasks on the same project simultaneously.
+4. **Cost-aware concurrency**:
+   - Estimate task cost from `estimate` field: S=cheap, M=moderate, L=expensive, XL=very expensive
+   - **Expensive tasks** (L, XL): max 2 concurrent
+   - **Cheap tasks** (S, M): fill remaining slots
+   - Target mix: 1-2 expensive + 2-3 cheap = 4-5 total
+5. **Slot limit**: Never exceed `--slots` (default 4).
+
+```python
+# Pseudocode for batch selection
+batch = []
+used_projects = set()
+expensive_count = 0
+
+for priority in ["P0", "P1", "P2"]:
+    for task in queue_items(priority, status="pending"):
+        if len(batch) >= MAX_SLOTS:
+            break
+        if task.project in used_projects:
+            continue  # One agent per project
+        if not deps_satisfied(task):
+            continue
+        if task.estimate in ("L", "XL"):
+            if expensive_count >= 2:
+                continue
+            expensive_count += 1
+        batch.append(task)
+        used_projects.add(task.project)
+```
+
+### Step 2: Assess and Dispatch
+
+For each task in the batch, decide the execution strategy:
+
+| Signal | Strategy | What happens |
+|--------|----------|-------------|
+| Estimate S, clear scope | **Direct** | Spawn Agent() with task description, no orchestration |
+| Estimate M, multi-file | **Direct+** | Spawn Agent() with task + "read code first, run tests after" |
+| Estimate L/XL, code | **Feature-dev style** | Agent explores → implements → self-reviews (see below) |
+| Estimate L/XL, writing | **PDCA** | Use af-run with writing domain archetypes |
+| Task contains "validate", "test", "lint", "check" | **Direct** | Cheap analytical task, no orchestration |
+| Task contains "review", "audit", "security" | **Review** | Spawn Guardian + relevant reviewers only |
+
+### L/XL Code Task Template (feature-dev style)
+
+For complex code tasks, give the agent a structured process instead of PDCA:
+
+```
+Agent(
+  description: "<project>: <task-short>",
+  prompt: "You are working on project <project> at <path>.
+    Task: <task description>
+
+    Follow this process:
+    1. EXPLORE: Read CLAUDE.md, docs/status.md, and the relevant source files.
+       Understand existing patterns before writing anything.
+    2. PLAN: Identify 2-3 files to change. Write a brief plan (what, where, why).
+       If ambiguous, list your assumptions.
+    3. IMPLEMENT: Make the changes. Follow existing code patterns strictly.
+    4. TEST: Run the project's test suite. Fix any failures.
+    5. SELF-REVIEW: Before committing, re-read your diff. Check:
+       - Error handling: what happens when this fails?
+       - Protocol compliance: am I using the right function signatures?
+       - Tests: did I test the important paths?
+    6. COMMIT + PUSH: Conventional commits, signed, pushed.
+
+    <standard rules>
+
+    STATUS: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED"
+)
+```
+
+This gives the agent feature-dev's structured exploration without the multi-agent overhead.
+For writing/research L/XL tasks, use af-run instead — archetypes add value where linters don't exist.
+
+**Agent spawn template:**
+
+For each task in the batch, spawn an Agent in the SAME message (parallel dispatch):
+
+```
+Agent(
+  description: "<project>: <task-short>",
+  prompt: "You are working on project <project> at <path>.
+    Task: <task description>
+    <notes if any>
+
+    Rules:
+    - Read the project's CLAUDE.md first
+    - Commit with: git -c user.signingkey=/home/c/.ssh/id_ed25519_dev.pub commit
+    - NO Co-Authored-By trailers
+    - Conventional commits
+    - Push when done: GIT_SSH_COMMAND='ssh -i /home/c/.ssh/id_ed25519_dev -o IdentitiesOnly=yes' git push origin main
+    - Run tests if the project has them
+    - Report: what you did, what changed, any blockers
+
+    STATUS: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED",
+  subagent_type: "general-purpose",
+  isolation: "worktree"  # Only for L/XL tasks; S/M tasks run directly
+)
+```
+
+**CRITICAL: Spawn all batch agents in a SINGLE message.** This enables parallel execution.
+Do not spawn them sequentially.
+
+### Step 3: Mark Running
+
+After spawning, update the queue:
+
+```bash
+# For each spawned task
+./scripts/ws start <task-id>  # or manually update queue.json status to "running"
+```
+
+If `./scripts/ws start` doesn't exist, update queue.json directly:
+```python
+task["status"] = "running"
+# Write back to docs/orchestra/queue.json
+```
+
+### Step 4: Collect Results
+
+As agents complete, process their results:
+
+1. **Parse status token** from agent output (last line: `STATUS: DONE|...`)
+2. **Based on status**:
+   - `DONE` → mark completed, note result
+   - `DONE_WITH_CONCERNS` → mark completed, log concerns for user review
+   - `NEEDS_CONTEXT` → mark pending, add concern to notes, skip for now
+   - `BLOCKED` → mark failed, add blocker to notes
+3. **Update queue**:
+   ```bash
+   ./scripts/ws done <task-id> -r "<summary of what was done>"
+   # or
+   ./scripts/ws fail <task-id> -r "<reason>"
+   ```
+
+### Step 5: Report and Loop
+
+After batch completes, show sprint status:
+
+```
+── Sprint Batch 1 ──────────────────────────────
+  ✓ writing.colette    fanout run           done (45s)
+  ✓ book.3sets         validation           done (30s)
+  △ book.sos           meta-book concept    needs_context (missing outline)
+  ✓ tool.archeflow     af-review mode       done (60s)
+
+Queue: 3 completed, 1 blocked, 3 remaining
+Next batch: 2 items ready
+────────────────────────────────────────────────
+```
+
+Then **immediately select and dispatch the next batch** (Step 1). Don't wait for user input in AUTONOM mode.
+
+### Step 6: Sprint Complete
+
+When no more tasks are schedulable (all done, blocked, or P3-only):
+
+1. Update `docs/control-center.md` Handoff section
+2. Run `./scripts/ws log --summary "<sprint summary>"` if available
+3. Show final sprint report:
+
+```
+── Sprint Complete ─────────────────────────────
+Duration: 12 min
+Tasks: 5 completed, 1 blocked, 1 remaining (P3)
+Projects touched: 4
+Commits: 7
+────────────────────────────────────────────────
+```
+
+---
+
+## Mode Behavior
+
+### AUTONOM
+- Dispatch immediately, no user confirmation
+- Commit + push after each agent completes
+- Only pause for BLOCKED tasks or budget exhaustion
+- Report between batches (one-line status)
+
+### ATTENDED
+- Show the selected batch before dispatching
+- Wait for user to approve: "Proceed with this batch? [y/n]"
+- After each batch, show results and ask: "Continue to next batch? [y/n/edit]"
+- "edit" lets the user reprioritize before next batch
+
+### PAUSED
+- Show queue status only
+- Do not dispatch any agents
+- Useful for reviewing state between sessions
+
+---
+
+## When to Use ArcheFlow Orchestration Within Sprint
+
+Most sprint tasks should be **direct agent dispatch** (no PDCA/pipeline overhead).
+Only escalate to full orchestration when:
+
+| Signal | Action |
+|--------|--------|
+| Task is S/M, clear scope, single project | Direct dispatch |
+| Task is L/XL | Use pipeline or PDCA strategy |
+| Task mentions "security", "auth", "encryption" | Add Guardian review |
+| Task is a review/audit | Spawn reviewers only (af-review mode) |
+| Task failed in a previous sprint | Escalate to PDCA with Explorer |
+
+The sprint runner's job is **throughput**, not perfection. Ship fast, fix forward.
+
+---
+
+## Integration with Existing Tools
+
+| Tool | How sprint uses it |
+|------|-------------------|
+| `./scripts/ws next` | Get next schedulable task |
+| `./scripts/ws done <id>` | Mark task completed |
+| `./scripts/ws fail <id>` | Mark task failed |
+| `./scripts/ws orient` | Initial workspace overview |
+| `./scripts/ws validate` | Pre-flight queue validation |
+| `git` per project | Commit + push after each agent |
+| `archeflow:run` | Only for L/XL tasks needing PDCA |
+
+---
+
+## Error Recovery
+
+- **Agent crashes mid-task**: Mark task as `failed`, add error to notes, continue with next batch
+- **Git push fails**: Log the error, do NOT retry. User will handle push conflicts manually.
+- **Queue file corrupted**: Run `./scripts/ws validate`. If invalid, stop sprint and report.
+- **Budget exceeded**: Stop sprint, report remaining tasks and estimated cost.
+- **All tasks blocked**: Report dependency graph, suggest which blockers to resolve first.

skills/using-archeflow/SKILL.md

@@ -11,22 +11,33 @@ Multi-agent orchestration using archetypal roles and PDCA quality cycles.
 
 On activation, print ONE line:
 ```
-archeflow v0.6.0 · 25 skills · <domain> domain
+archeflow v0.7.0 · 25 skills · <domain> domain
 ```
 Where `<domain>` is auto-detected: `writing` if `colette.yaml` exists, `research` if paper/thesis files exist, `code` otherwise. Then proceed silently — no further announcement unless `archeflow:run` is invoked.
 
 During runs, follow the `archeflow:presence` skill for output format: show outcomes not mechanics, one line per phase, value at the end.
 
-## IMPORTANT: When to Activate
+## IMPORTANT: When to Use What
 
-You MUST use ArcheFlow orchestration (load `archeflow:orchestration` skill and follow its steps) for any task that matches:
+### Use `/af-sprint` (primary mode) when:
+- User says "run the sprint", "work the queue", "go autonomous"
+- Multiple tasks are pending across projects
+- The workspace queue (docs/orchestra/queue.json) has pending items
 
-- **New features** -- any feature touching 2+ files
+### Use `/af-review` when:
-- **Refactoring** -- structural changes across modules
+- User wants to review code before merging
-- **Security-sensitive changes** -- auth, encryption, input handling, API keys
+- A diff, branch, or commit range needs quality check
-- **Bug fixes with unclear root cause** -- use Explorer to investigate first
+- Security-sensitive changes need Guardian analysis
-- **Code review requests** -- spawn Guardian + relevant reviewers
+
-- **Multi-file changes** -- anything beyond a single-file edit
+### Use `/af-run` (deep orchestration) when:
+- **Writing/research tasks** -- archetypes add value where linters don't exist
+- **Security-sensitive code changes** -- auth, encryption, API keys
+- **Complex multi-module refactors** with unclear approach
+
+### Do NOT use ArcheFlow for:
+- **Single-feature code development** -- use `feature-dev` plugin or work directly
+- **Simple fixes** -- just do them
+- **Questions, exploration, reading** -- no code changes needed
 
 Choose the workflow based on risk:
 
@@ -146,7 +157,6 @@ Read `.archeflow/session-log.md` and show the last 5 orchestration summaries in
 
 ### Quality and Safety
 - **archeflow:shadow-detection** -- Quantitative dysfunction detection and correction
-- **archeflow:attention-filters** -- Context optimization per archetype
 - **archeflow:convergence** -- Detects convergence, stalling, and oscillation in multi-cycle runs
 - **archeflow:artifact-routing** -- Inter-phase artifact protocol for naming, storage, and routing
 

skills/workflow-design/SKILL.md

@@ -25,6 +25,10 @@ ArcheFlow's PDCA cycles spiral upward through iterations — each cycle incorpor
 │         Plan (design)     ← Cycle 1 (initial)
 ```
 
+## Strategy vs Workflow
+
+A **strategy** defines the execution shape: PDCA is cyclic (Plan-Do-Check-Act with feedback loops), pipeline is linear (Plan-Implement-Review-Verify, no cycle-back). A **workflow** defines the depth: fast uses fewer agents and cycles, thorough uses more. Strategy and workflow are orthogonal — you can run a `fast` workflow with either strategy, though `thorough` always uses PDCA because linear flows cannot iterate on findings.
+
 ## Built-in Workflows
 
 ### `fast` — Single Turn