feat: workflow intelligence, quality loop, completion promises, parallel teams

Sprint 1 — Workflow Intelligence (A1-A3):
- Conditional escalation: fast→standard on 2+ CRITICALs
- Guardian fast-path: skip remaining reviewers on clean pass
- Confidence-triggered escalation: pause/upgrade/probe on low scores

Sprint 2 — Quality Loop (B1-B2, B5-B6):
- Maker self-review checklist before submitting to Check phase
- Proposal diff ("What Changed") on cycle 2+ revisions
- Convergence detection: escalate to user if same finding persists 2 cycles
- Cross-archetype dedup: merge duplicate findings from different reviewers

Sprint 3 — Completion & Verification (B3-B4):
- Completion promise: user-defined done criteria checked in Act phase
- Post-merge verification: run tests on main, auto-revert on failure

Sprint 4 — Parallel & Scale (C1-C4):
- Parallel team orchestration: 2-3 independent teams with merge gate
- Task dependency graph in autonomous queue format
- Auto-resume on interruption via .archeflow/state.json
- Budget-aware scheduling with automatic workflow downgrade

skills/orchestration/SKILL.md

@@ -17,6 +17,38 @@ Assess the task and pick:
 | Feature, multiple files, moderate risk | `standard` (2 cycles) |
 | Security-sensitive, breaking changes, public API | `thorough` (3 cycles) |
 
+## Workflow Adaptation Rules
+
+The initial workflow choice is a starting point, not a commitment. These rules adapt the workflow at runtime based on signals from Creator and Guardian. Evaluate in order after each relevant phase.
+
+### A1: Conditional Escalation (fast → standard)
+
+**When:** Guardian rejects with 2+ CRITICAL findings in a `fast` workflow.
+**Action:** Escalate to `standard` for the next cycle — add Skeptic + Sage to the reviewer roster.
+**Why:** If Guardian found serious issues, more perspectives help find root causes.
+**Override:** If A3 already escalated to `thorough`, do nothing (already higher).
+
+### A2: Guardian Fast-Path (skip remaining reviewers)
+
+**When:** Guardian finds 0 CRITICAL and 0 WARNING in a `standard` or `thorough` workflow.
+**Action:** Skip Skeptic, Sage, and Trickster. Proceed directly to Act phase (merge).
+**Why:** Guardian's security review is the strictest gate. Clean pass = safe to merge without additional review cost.
+**Override:** Suppressed if A1 just triggered in the same cycle. Do not fast-path an escalated workflow.
+**Log:** Note "Guardian fast-path taken — remaining reviewers skipped" in orchestration report.
+
+### A3: Confidence-Triggered Escalation
+
+**When:** Creator's confidence table has any axis below 0.5.
+**Action by axis:**
+
+| Axis | Score < 0.5 Action |
+|------|-------------------|
+| Task understanding | **Pause.** Ask user to clarify. Do not proceed until >0.5 or user overrides. |
+| Solution completeness | **Upgrade to standard.** Add Explorer before proceeding. |
+| Risk coverage | **Spawn mini-Explorer** for the specific risky area (parallel, 5 min max). Don't block other phases. |
+
+Multiple axes can trigger simultaneously — handle in parallel.
+
 ## Step 1: Plan Phase
 
 Spawn agents sequentially — Creator needs Explorer's findings.
@@ -97,7 +129,14 @@ Agent(
     3. Commit with descriptive messages
     4. Run existing tests — nothing may break
     5. If the proposal is unclear, implement your best interpretation and note it
-    Do NOT skip tests. Do NOT refactor unrelated code.",
+    Do NOT skip tests. Do NOT refactor unrelated code.
+
+    BEFORE finishing — Self-Review Checklist:
+    1. Did I change ALL files listed in the proposal's Changes section?
+    2. Did I add tests for each behavioral change?
+    3. Are there files in my diff NOT listed in the proposal? If yes, revert them.
+    4. Do all existing tests still pass?
+    Report any gaps in your Implementation summary.",
   isolation: "worktree",
   mode: "bypassPermissions"
 )
@@ -199,13 +238,27 @@ Agent(
 
 ## Step 4: Act Phase
 
-Collect all reviewer outputs and decide:
+Collect all reviewer outputs and decide.
 
-### All Approved
+### Completion Promise (optional)
+
+If the user defined explicit done criteria with the task, check them now:
+
+```
+Completion criteria: <test command passes> AND <Guardian approves>
+Example: "done when pytest passes and Guardian approves with 0 CRITICAL"
+```
+
+If completion criteria are defined, **all criteria must pass** — reviewer approval alone is not sufficient. If tests fail but reviewers approved, cycle back with "tests failing" as feedback to Creator.
+
+### All Approved (and completion criteria met)
 1. Merge the Maker's worktree branch into the target branch
-2. Report: what was implemented, what was reviewed, any warnings noted
-3. Clean up the worktree
-4. Record metrics (see Orchestration Metrics)
+2. **Post-merge verification:** Run the project's test suite on the merged branch
+   - Tests pass → proceed to step 3
+   - Tests fail → **auto-revert** the merge commit, report the failure, and cycle back with "integration test failure on main" as feedback
+3. Report: what was implemented, what was reviewed, any warnings noted
+4. Clean up the worktree
+5. Record metrics (see Orchestration Metrics)
 
 ### Issues Found (and cycles remaining)
 1. Build structured feedback using the Cycle Feedback Protocol below
@@ -266,6 +319,24 @@ Compare cycle N findings against cycle N-1:
 
 This prevents regression and gives the Creator/Maker a clear list of what to address.
 
+### 4. Convergence Detection
+
+If the **same finding** (same category + same file location) appears **unresolved in 2 consecutive cycles**, escalate to user:
+
+> "Finding persists across 2 cycles: [Guardian] CRITICAL security — SQL injection in src/auth.ts:48. This may need human judgment or a different approach."
+
+Do not cycle again blindly. The issue is likely structural (wrong design, not wrong implementation) and needs human input.
+
+### 5. Cross-Archetype Dedup
+
+If two reviewers raise the same issue (same file + same category + similar description), merge into one finding in the consolidated output:
+
+```
+| Guardian + Skeptic | CRITICAL | security | Input not sanitized (src/api.ts:30) | Add validation |
+```
+
+Don't double-count in severity tallies. Route to the higher-priority destination (Creator over Maker).
+
 ---
 
 ## Orchestration Metrics
@@ -364,6 +435,31 @@ On detection: apply correction prompt from `archeflow:shadow-detection` skill. O
 
 ---
 
+## Parallel Team Orchestration
+
+When running multiple independent tasks, spawn parallel ArcheFlow teams. Each team runs its own PDCA cycle on a separate worktree.
+
+### Rules
+
+1. **Non-overlapping file scope:** Each team must work on different files. If two tasks touch the same file, run them sequentially.
+2. **Independent worktrees:** Each team's Maker gets its own worktree branch (`archeflow/team-1-maker`, `archeflow/team-2-maker`).
+3. **First-finished-first-merged:** Teams merge in completion order. Later teams rebase onto the updated main before their own merge.
+4. **Merge conflict handling:** If rebase fails, the later team re-runs its Check phase against the merged main. If conflicts are structural, escalate to user.
+5. **Max 3 parallel teams:** More causes diminishing returns and merge headaches.
+
+### Spawning Parallel Teams
+
+```
+# Launch 2-3 teams in a single message with multiple Agent calls:
+Agent(description: "🏗️ Team 1: pagination fix (fast)", ...)
+Agent(description: "🏗️ Team 2: JWT auth (standard)", ...)
+Agent(description: "🏗️ Team 3: logging refactor (fast)", ...)
+```
+
+Each team follows the full PDCA steps independently. The orchestrator monitors all teams and handles merges.
+
+---
+
 ## Orchestration Report
 
 After completion, summarize: