fix: address review findings (rollback mainline, audit flag, confidence gate, test pattern, jq args)

- git revert uses --mainline 1 for merge commits
- inject dispatch passes all args so --audit flag is reachable
- confidence gate defaults to 0.0 (triggers gate) instead of 0.7 (bypasses)
- test-first grep uses word-boundary patterns to avoid false positives
- jq uses --arg instead of string interpolation for safe filtering

.claude-plugin/plugin.json

@@ -12,5 +12,14 @@
     "orchestration", "multi-agent", "archetypes", "pdca",
     "code-review", "quality", "worktrees", "jungian",
     "shadow-detection", "workflows"
-  ]
+  ],
+  "skills": [
+    "run", "orchestration", "plan-phase", "do-phase", "check-phase", "act-phase",
+    "shadow-detection", "attention-filters", "convergence", "artifact-routing",
+    "process-log", "memory", "effectiveness", "progress",
+    "colette-bridge", "git-integration", "multi-project",
+    "custom-archetypes", "workflow-design", "domains", "cost-tracking",
+    "templates", "autonomous-mode", "using-archeflow", "presence"
+  ],
+  "hooks": "hooks/hooks.json"
 }

README.md

@@ -16,14 +16,44 @@ The key insight: archetypes are not just system prompts. Each one has a **virtue
 
 ### 1. Install
 
-```bash
+**From the marketplace** (recommended):
-# From Git
-claude plugin install --url https://git.xorwell.de/c/claude-archeflow-plugin
 
-# Local development
+```bash
+# Add the marketplace (one time)
+/plugin marketplace add https://git.xorwell.de/c/claude-archeflow-plugin
+
+# Install the plugin
+/plugin install archeflow@claude-archeflow-plugin
+```
+
+**From Git URL directly:**
+
+```bash
+/plugin marketplace add https://git.xorwell.de/c/claude-archeflow-plugin.git
+/plugin install archeflow --scope user
+```
+
+**Local development:**
+
+```bash
 claude --plugin-dir ./archeflow
 ```
 
+After installing, run `/reload-plugins` or restart Claude Code. ArcheFlow activates automatically on session start.
+
+#### Verify installation
+
+```
+/plugin         # Opens plugin manager — check "Installed" tab
+/af-status      # Should show "no active run"
+```
+
+#### Scopes
+
+- `--scope user` — available in all your projects (recommended)
+- `--scope project` — only in the current project
+- `--scope local` — only in the current directory
+
 ### 2. Run your first orchestration
 
 Just describe a task. ArcheFlow activates automatically for multi-file changes:

hooks/session-start

@@ -25,7 +25,10 @@ try {
   }
 
   console.log(JSON.stringify({
-    hookSpecificOutput: { additionalContext: stripped }
+    hookSpecificOutput: {
+      hookEventName: "SessionStart",
+      additionalContext: stripped
+    }
   }));
 } catch (e) {
   console.log("{}");

lib/archeflow-memory.sh

@@ -201,6 +201,16 @@ cmd_inject() {
   local domain="${1:-}"
   local archetype="${2:-}"
 
+  # Parse optional --audit <run_id>
+  local audit_run_id=""
+  shift 2 2>/dev/null || true
+  while [[ $# -gt 0 ]]; do
+    case "$1" in
+      --audit) audit_run_id="$2"; shift 2 ;;
+      *) shift ;;
+    esac
+  done
+
   if [[ ! -f "$LESSONS_FILE" ]]; then
     return 0
   fi
@@ -237,14 +247,118 @@ cmd_inject() {
     return 0
   fi
 
+  # Collect injected lesson IDs for audit
+  local injected_ids=()
+
   echo "## Known Issues (from past runs)"
   while IFS= read -r lesson; do
-    local desc freq src
+    local desc freq src lid
     desc=$(echo "$lesson" | jq -r '.description')
     freq=$(echo "$lesson" | jq -r '.frequency')
     src=$(echo "$lesson" | jq -r '.source')
+    lid=$(echo "$lesson" | jq -r '.id')
+    injected_ids+=("$lid")
     echo "- ${desc} [seen ${freq}x, ${src}]"
   done <<< "$lessons"
+
+  # Write audit record if --audit was passed
+  if [[ -n "$audit_run_id" && ${#injected_ids[@]} -gt 0 ]]; then
+    ensure_dir
+    local AUDIT_FILE="${MEMORY_DIR}/audit.jsonl"
+    local ids_json
+    ids_json=$(printf '%s\n' "${injected_ids[@]}" | jq -R . | jq -sc .)
+    jq -cn \
+      --arg ts "$(now_ts)" \
+      --arg run_id "$audit_run_id" \
+      --arg domain "$domain" \
+      --arg archetype "$archetype" \
+      --argjson lessons_injected "$ids_json" \
+      --argjson lesson_count "${#injected_ids[@]}" \
+      '{ts:$ts,run_id:$run_id,domain:$domain,archetype:$archetype,lessons_injected:$lessons_injected,lesson_count:$lesson_count}' \
+      >> "$AUDIT_FILE"
+  fi
+}
+
+cmd_audit_check() {
+  local run_id="${1:?Usage: $0 audit-check <run_id>}"
+  local AUDIT_FILE="${MEMORY_DIR}/audit.jsonl"
+  local EVENTS_FILE=".archeflow/events/${run_id}.jsonl"
+
+  if [[ ! -f "$AUDIT_FILE" ]]; then
+    echo "No audit records found." >&2
+    return 0
+  fi
+
+  if [[ ! -f "$EVENTS_FILE" ]]; then
+    echo "No events file found for run $run_id." >&2
+    return 0
+  fi
+
+  # Get lessons injected for this run
+  local injected
+  injected=$(jq -c --arg rid "$run_id" 'select(.run_id == $rid)' "$AUDIT_FILE" 2>/dev/null || true)
+
+  if [[ -z "$injected" ]]; then
+    echo "No audit records for run $run_id." >&2
+    return 0
+  fi
+
+  # Get all finding descriptions from review.verdict events
+  local finding_descs
+  finding_descs=$(jq -r '
+    select(.type == "review.verdict") |
+    .data.findings[]? | .description // empty
+  ' "$EVENTS_FILE" 2>/dev/null | tr '[:upper:]' '[:lower:]' || true)
+
+  # For each injected lesson, check if findings match the lesson's topic
+  local lesson_ids
+  lesson_ids=$(echo "$injected" | jq -r '.lessons_injected[]' 2>/dev/null | sort -u)
+
+  while IFS= read -r lid; do
+    [[ -z "$lid" ]] && continue
+
+    # Get lesson description
+    local lesson_desc
+    lesson_desc=$(jq -r --arg lid "$lid" 'select(.id == $lid) | .description' "$LESSONS_FILE" 2>/dev/null | head -1)
+    [[ -z "$lesson_desc" ]] && continue
+
+    # Check keyword overlap between lesson and findings
+    local lesson_tokens finding_overlap
+    lesson_tokens=$(tokenize "$lesson_desc")
+    finding_overlap=0
+
+    if [[ -n "$finding_descs" ]]; then
+      local finding_tokens
+      finding_tokens=$(echo "$finding_descs" | tr -cs '[:alnum:]' '\n' | awk 'length >= 3' | sort -u)
+      local common
+      common=$(comm -12 <(echo "$lesson_tokens") <(echo "$finding_tokens") | wc -l)
+      local total
+      total=$(echo "$lesson_tokens" | wc -l)
+      if [[ "$total" -gt 0 ]]; then
+        finding_overlap=$(( common * 100 / total ))
+      fi
+    fi
+
+    local effectiveness
+    if [[ "$finding_overlap" -ge 30 ]]; then
+      effectiveness="ineffective"  # Issue repeated despite lesson injection
+    else
+      effectiveness="helpful"  # Issue was prevented (no matching finding)
+    fi
+
+    # Append result to audit.jsonl
+    jq -cn \
+      --arg ts "$(now_ts)" \
+      --arg run_id "$run_id" \
+      --arg lesson_id "$lid" \
+      --arg lesson_desc "$lesson_desc" \
+      --arg effectiveness "$effectiveness" \
+      --argjson overlap "$finding_overlap" \
+      '{ts:$ts,run_id:$run_id,type:"effectiveness_check",lesson_id:$lesson_id,lesson_desc:$lesson_desc,effectiveness:$effectiveness,keyword_overlap_pct:$overlap}' \
+      >> "$AUDIT_FILE"
+
+    echo "[archeflow-memory] Lesson $lid ($effectiveness): $lesson_desc" >&2
+  done <<< "$lesson_ids"
 }
 
 cmd_add() {
@@ -383,11 +497,12 @@ if [[ $# -lt 1 ]]; then
   echo "" >&2
   echo "Commands:" >&2
   echo "  extract <events.jsonl>       Extract lessons from a completed run" >&2
-  echo "  inject <domain> <archetype>  Output relevant lessons for injection" >&2
+  echo "  inject <domain> <archetype> [--audit <run_id>]  Output relevant lessons for injection" >&2
   echo "  add <type> <description>     Manually add a lesson" >&2
   echo "  list                         List all active lessons" >&2
   echo "  decay                        Apply decay to all lessons" >&2
   echo "  forget <id>                  Archive a lesson by ID" >&2
+  echo "  audit-check <run_id>         Check lesson effectiveness for a run" >&2
   exit 1
 fi
 
@@ -400,7 +515,7 @@ case "$COMMAND" in
     cmd_extract "$1"
     ;;
   inject)
-    cmd_inject "${1:-}" "${2:-}"
+    cmd_inject "$@"
     ;;
   add)
     [[ $# -lt 2 ]] && { echo "Usage: $0 add <type> <description>" >&2; exit 1; }
@@ -416,6 +531,10 @@ case "$COMMAND" in
     [[ $# -lt 1 ]] && { echo "Usage: $0 forget <id>" >&2; exit 1; }
     cmd_forget "$1"
     ;;
+  audit-check)
+    [[ $# -lt 1 ]] && { echo "Usage: $0 audit-check <run_id>" >&2; exit 1; }
+    cmd_audit_check "$1"
+    ;;
   *)
     echo "Unknown command: $COMMAND" >&2
     exit 1

lib/archeflow-rollback.sh

@@ -0,0 +1,61 @@
+#!/usr/bin/env bash
+# archeflow-rollback.sh — Auto-revert a merge that fails post-merge tests.
+#
+# Usage: archeflow-rollback.sh <run_id> [--test-cmd <cmd>]
+#
+# If --test-cmd not provided, reads test_command from .archeflow/config.yaml.
+# Returns 0 if tests pass, 1 if tests fail (merge reverted).
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+RUN_ID="${1:?Usage: archeflow-rollback.sh <run_id> [--test-cmd <cmd>]}"
+shift
+
+# Parse optional --test-cmd
+TEST_CMD=""
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --test-cmd) TEST_CMD="$2"; shift 2 ;;
+    *) echo "Unknown option: $1" >&2; exit 2 ;;
+  esac
+done
+
+# Read test_command from config if not provided
+if [[ -z "$TEST_CMD" ]]; then
+  if [[ -f ".archeflow/config.yaml" ]]; then
+    TEST_CMD=$(grep -E "^test_command:" .archeflow/config.yaml | sed 's/^test_command:\s*//' | tr -d '"' || true)
+  fi
+fi
+
+if [[ -z "$TEST_CMD" ]]; then
+  echo "ERROR: No test command specified (use --test-cmd or set test_command in .archeflow/config.yaml)" >&2
+  exit 2
+fi
+
+# Verify HEAD is an ArcheFlow merge
+HEAD_MSG=$(git log -1 --format=%s HEAD)
+if [[ "$HEAD_MSG" != *"$RUN_ID"* ]] && [[ "$HEAD_MSG" != *"archeflow"* ]]; then
+  echo "WARNING: HEAD commit does not appear to be an ArcheFlow merge: $HEAD_MSG" >&2
+  echo "Proceeding anyway..." >&2
+fi
+
+echo "Running post-merge tests: $TEST_CMD"
+
+if timeout 300 bash -c "$TEST_CMD"; then
+  echo "Tests passed — merge is good."
+  exit 0
+fi
+
+echo "Tests FAILED — reverting merge..."
+git revert --no-edit --mainline 1 HEAD
+
+# Emit event if event script exists
+if [[ -x "$SCRIPT_DIR/archeflow-event.sh" ]]; then
+  "$SCRIPT_DIR/archeflow-event.sh" "$RUN_ID" decision act "" \
+    "{\"what\":\"post_merge_test\",\"chosen\":\"revert\",\"rationale\":\"test suite failed after merge\"}" ""
+fi
+
+REVERT_HASH=$(git rev-parse --short HEAD)
+echo "Merge reverted (commit: $REVERT_HASH). Tests must pass before re-merging."
+exit 1

skills/act-phase/SKILL.md

@@ -286,18 +286,20 @@ When cycling back, produce `act-feedback.md` as a structured handoff. This repla
 | — | — | — | — | — |
 ```
 
-**Routing rules** (same as orchestration skill, repeated here for self-containment):
+**Routing rules** (canonical table — matches orchestration and artifact-routing skills):
 
-| Finding Source | Routes to | When |
+| Source | Category | Routes to | Reason |
-|----------------|-----------|------|
+|--------|----------|-----------|--------|
-| Guardian (security, breaking-change) | Creator | Design must change |
+| Guardian | security, breaking-change | Creator | Design must change |
-| Skeptic (design, scalability) | Creator | Assumptions need revision |
+| Guardian | reliability, dependency | Creator | Architectural decision needed |
-| Sage (quality, consistency) | Maker | Implementation refinement |
+| Skeptic | design, scalability | Creator | Assumptions need revision |
-| Sage (design) | Creator | If it's an architectural concern |
+| Sage | quality, consistency | Maker | Implementation refinement |
-| Trickster (reliability) | Creator | If root cause is a design flaw |
+| Sage | testing | Maker | Test gap, not design flaw |
-| Trickster (testing) | Maker | If root cause is a test gap |
+| Trickster | reliability (design flaw) | Creator | Needs redesign |
+| Trickster | reliability (test gap) | Maker | Needs more tests |
+| Trickster | testing | Maker | Edge case not covered |
 
-When in doubt about routing: if the fix requires changing the approach, route to Creator. If the fix requires changing the code within the existing approach, route to Maker.
+**Disambiguation rule:** When in doubt: if the fix requires changing the approach, route to Creator. If it requires changing the code within the existing approach, route to Maker.
 
 ---
 

skills/artifact-routing/SKILL.md

@@ -46,6 +46,7 @@ Artifacts follow the pattern: `<phase>-<agent>.<ext>`
 |-------|-------|----------|--------|
 | plan | explorer | `plan-explorer.md` | Markdown research report |
 | plan | creator | `plan-creator.md` | Markdown proposal with confidence scores |
+| plan | mini-explorer | `plan-mini-explorer.md` | Focused risk research (only if confidence gate triggers) |
 | do | maker | `do-maker.md` | Markdown implementation summary |
 | do | maker | `do-maker-files.txt` | Plain text, one file path per line |
 | check | guardian | `check-guardian.md` | Markdown verdict + findings table |
@@ -89,8 +90,8 @@ Note: Address each unresolved issue listed above. Explain how your revised propo
 
 | Agent | Receives | Does NOT receive |
 |-------|----------|-----------------|
-| **Maker** (cycle 1) | `plan-creator.md` (the proposal) | `plan-explorer.md`, reviewer outputs, raw task description |
+| **Maker** (cycle 1) | `plan-creator.md` (the proposal), `plan-mini-explorer.md` (if exists) | `plan-explorer.md`, reviewer outputs, raw task description |
-| **Maker** (cycle 2+) | `plan-creator.md`, Maker-routed findings from `act-feedback.md` | Explorer research, Guardian/Skeptic findings (those went to Creator) |
+| **Maker** (cycle 2+) | `plan-creator.md`, `plan-mini-explorer.md` (if exists), Maker-routed findings from `act-feedback.md` | Explorer research, Guardian/Skeptic findings (those went to Creator) |
 
 **Maker context injection template (cycle 2+):**
 ```markdown
@@ -164,6 +165,8 @@ No agents are spawned in Act. The orchestrator reads all `check-*.md` artifacts
 
 ## Feedback Routing
 
+> **This is the canonical routing table.** Other skills (orchestration, act-phase) must match this table exactly. When updating routing rules, update this table first, then sync the others.
+
 When building `act-feedback.md` after the Check phase, route each finding to the right agent for the next cycle:
 
 | Finding Source | Finding Category | Routes To | Rationale |
@@ -177,7 +180,7 @@ When building `act-feedback.md` after the Check phase, route each finding to the
 | Trickster | reliability (test gap) | **Maker** | Needs more tests |
 | Trickster | testing | **Maker** | Edge case not covered |
 
-**Ambiguous cases:** If a Trickster finding could be either a design flaw or a test gap, check: does the fix require changing the proposal's architecture/approach, or just adding a test/validation? Architecture change → Creator. Additional test → Maker.
+**Disambiguation rule:** When in doubt: if the fix requires changing the approach, route to Creator. If it requires changing the code within the existing approach, route to Maker.
 
 ### Feedback File Format
 
@@ -252,6 +255,7 @@ Before injecting an artifact into an agent's context, always check if the file e
 | Artifact | Missing when |
 |----------|-------------|
 | `plan-explorer.md` | Fast workflow (no Explorer) |
+| `plan-mini-explorer.md` | Confidence gate did not trigger for risk coverage |
 | `check-skeptic.md` | Fast workflow, or A2 fast-path taken |
 | `check-sage.md` | Fast workflow, or A2 fast-path taken |
 | `check-trickster.md` | Non-thorough workflow, or A2 fast-path taken |

skills/do-phase/SKILL.md

@@ -165,3 +165,29 @@ Before your final commit, verify:
 - [ ] Every logical step has its own commit
 - [ ] Output summary is complete and accurate
 - [ ] Branch name follows convention
+
+## Test-First Gate
+
+Before the Maker's output is accepted, the orchestrator validates that tests were included.
+
+### Validation Logic
+
+Read `do-maker-files.txt`. Check if any file path matches common test patterns:
+- `*test*`, `*spec*`, `*.test.*`, `*.spec.*`, `*_test.*`, `*_spec.*`
+- Files in directories named `test/`, `tests/`, `__tests__/`, `spec/`
+
+For writing domain projects, this gate is skipped.
+
+### Outcomes
+
+| Result | Action |
+|--------|--------|
+| Test files found | Pass — proceed to Check phase |
+| No test files, code domain | **Warn** — emit WARNING event, note in do-maker.md |
+| No test files + Creator specified tests | **Block** — re-run Maker with test instruction (1 retry) |
+| Writing domain | Skip gate entirely |
+
+The block case triggers a targeted re-run with prompt:
+"The proposal specified these test cases: <test strategy section>. No test files
+were found in your changes. Add the specified tests before finishing."
+This is one retry within the Do phase, not a full PDCA cycle.

skills/git-integration/SKILL.md

@@ -219,6 +219,32 @@ The helper script reads this config if it exists. All values have sensible defau
 
 ---
 
+## Post-Merge Rollback
+
+After merging, the run skill validates the merge by running the project's test suite. If tests fail, the merge is automatically reverted.
+
+### Script
+
+```bash
+./lib/archeflow-rollback.sh <run_id> [--test-cmd <cmd>]
+```
+
+**Behavior:**
+1. Reads `test_command` from `.archeflow/config.yaml` (or uses `--test-cmd` override)
+2. Runs the test suite with a 5-minute timeout
+3. If tests pass: exits 0 (merge is good)
+4. If tests fail: runs `git revert --no-edit HEAD`, emits a `decision` event, exits 1
+5. Verifies HEAD is an ArcheFlow merge commit before reverting (warning if not, proceeds anyway)
+
+**Integration with run skill:** Called in section 4c (All Approved) after `archeflow-git.sh merge`. If it returns non-zero, the orchestrator cycles back with "integration test failure" feedback or reports to the user if max cycles are reached.
+
+**Configuration:** Set `test_command` in `.archeflow/config.yaml`:
+```yaml
+test_command: "npm test"       # or "pytest", "cargo test", etc.
+```
+
+---
+
 ## Safety Rules
 
 These rules are inherited from `archeflow:orchestration` and reinforced here:

skills/memory/SKILL.md

@@ -215,6 +215,59 @@ Moves the lesson to `archive.jsonl` regardless of frequency.
 | Before agent spawn (run start) | Inject relevant lessons | `archeflow-memory.sh inject <domain> <archetype>` |
 | User command | Add/list/forget lessons | `archeflow-memory.sh add/list/forget` |
 
+## Audit Trail
+
+Track which lessons are injected into each run and whether they were effective.
+
+### Storage
+
+```
+.archeflow/memory/audit.jsonl    # Append-only audit log
+```
+
+### Injection Audit Record
+
+When `--audit <run_id>` is passed to the `inject` command, an audit record is written:
+
+```jsonl
+{"ts":"2026-04-04T10:00:00Z","run_id":"2026-04-04-auth-fix","domain":"code","archetype":"","lessons_injected":["m-001","m-003"],"lesson_count":2}
+```
+
+Usage:
+```bash
+./lib/archeflow-memory.sh inject "$DOMAIN" "" --audit "$RUN_ID"
+```
+
+### Effectiveness Check
+
+After a run completes, check whether injected lessons prevented issues:
+
+```bash
+./lib/archeflow-memory.sh audit-check <run_id>
+```
+
+This command:
+1. Reads `audit.jsonl` for lessons injected in the given run
+2. Reads the run's event file for `review.verdict` events
+3. For each injected lesson, checks keyword overlap between the lesson's description and review findings
+4. **No matching finding** = `helpful` (the lesson likely prevented the issue)
+5. **Matching finding** = `ineffective` (the issue repeated despite the lesson being injected)
+6. Appends effectiveness results to `audit.jsonl`
+
+### Effectiveness Over Time
+
+By querying `audit.jsonl` for effectiveness records, you can measure:
+- Which lessons consistently prevent issues (high `helpful` count)
+- Which lessons are not working (high `ineffective` count — consider rewording or removing)
+- Overall memory system ROI (ratio of helpful to ineffective across all runs)
+
+```bash
+# Count effectiveness per lesson
+jq -r 'select(.type == "effectiveness_check") | [.lesson_id, .effectiveness] | @tsv' .archeflow/memory/audit.jsonl | sort | uniq -c
+```
+
+---
+
 ## Design Principles
 
 1. **Append-only storage.** `lessons.jsonl` is append-only during writes; decay rewrites the file in place but preserves all data (archived lessons move to `archive.jsonl`).

skills/orchestration/SKILL.md

@@ -344,12 +344,18 @@ Parse each reviewer's output into the standardized format:
 
 Not all findings go to the same agent:
 
-| Finding source | Routes to | Rationale |
+| Source | Category | Routes to | Reason |
-|----------------|-----------|-----------|
+|--------|----------|-----------|--------|
-| Guardian (security, breaking-change) | **Creator** | Design must change |
+| Guardian | security, breaking-change | **Creator** | Design must change |
-| Skeptic (design, scalability) | **Creator** | Assumptions need revision |
+| Guardian | reliability, dependency | **Creator** | Architectural decision needed |
-| Sage (quality, consistency) | **Maker** | Implementation refinement |
+| Skeptic | design, scalability | **Creator** | Assumptions need revision |
-| Trickster (reliability, testing) | **Creator** if design flaw, **Maker** if test gap | Depends on root cause |
+| Sage | quality, consistency | **Maker** | Implementation refinement |
+| Sage | testing | **Maker** | Test gap, not design flaw |
+| Trickster | reliability (design flaw) | **Creator** | Needs redesign |
+| Trickster | reliability (test gap) | **Maker** | Needs more tests |
+| Trickster | testing | **Maker** | Edge case not covered |
+
+**Disambiguation rule:** When in doubt: if the fix requires changing the approach, route to Creator. If it requires changing the code within the existing approach, route to Maker.
 
 ### 3. Track Resolution
 

skills/run/SKILL.md

@@ -63,6 +63,25 @@ 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.
 
+#### 0b. Memory Injection
+
+Load cross-run memory lessons and inject into agent prompts. Use `--audit` to track which lessons were injected for this run:
+
+```bash
+# Load cross-run memory for this domain (with audit trail)
+MEMORY_LESSONS=$(./lib/archeflow-memory.sh inject "$DOMAIN" "" --audit "$RUN_ID")
+
+# Inject into Explorer/Creator prompts if non-empty
+if [[ -n "$MEMORY_LESSONS" ]]; then
+  EXPLORER_PROMPT="${EXPLORER_PROMPT}
+
+${MEMORY_LESSONS}"
+  CREATOR_PROMPT="${CREATOR_PROMPT}
+
+${MEMORY_LESSONS}"
+fi
+```
+
 ---
 
 ### 1. Plan Phase
@@ -126,17 +145,83 @@ After Creator returns:
 
 #### 1c. Confidence Gate (Adaptation Rule A3)
 
-Read Creator's confidence scores from `plan-creator.md`. Apply A3 per `archeflow:orchestration`:
+**Parsing instructions:**
-- Task understanding < 0.5 → **Pause**, ask user
+
-- Solution completeness < 0.5 → **Upgrade** to standard, spawn Explorer
+Read `plan-creator.md`, locate the `### Confidence` table. Extract scores for each axis as floats:
-- Risk coverage < 0.5 → **Spawn mini-Explorer** for risky area (parallel, 5 min max)
+
+```bash
+CONF_FILE=".archeflow/artifacts/${RUN_ID}/plan-creator.md"
+
+# Extract confidence scores (expects format: "| Task understanding | 0.8 |")
+TASK_UNDERSTANDING=$(grep -i "task understanding" "$CONF_FILE" | grep -oE '[0-9]+\.[0-9]+' | head -1)
+SOLUTION_COMPLETENESS=$(grep -i "solution completeness" "$CONF_FILE" | grep -oE '[0-9]+\.[0-9]+' | head -1)
+RISK_COVERAGE=$(grep -i "risk coverage" "$CONF_FILE" | grep -oE '[0-9]+\.[0-9]+' | head -1)
+
+# Fallback: if unparseable, emit warning and default to 0.0 (triggers gate, not bypasses it)
+if [[ -z "$TASK_UNDERSTANDING" || -z "$SOLUTION_COMPLETENESS" || -z "$RISK_COVERAGE" ]]; then
+  echo "WARNING: Could not parse confidence scores from plan-creator.md" >&2
+  ./lib/archeflow-event.sh "$RUN_ID" decision plan "" \
+    '{"what":"confidence_parse_failure","chosen":"warn","rationale":"one or more scores unparseable"}' "$SEQ_CREATOR_COMPLETE"
+fi
+TASK_UNDERSTANDING="${TASK_UNDERSTANDING:-0.0}"
+SOLUTION_COMPLETENESS="${SOLUTION_COMPLETENESS:-0.0}"
+RISK_COVERAGE="${RISK_COVERAGE:-0.0}"
+```
+
+**Pause branch** (Task understanding < 0.5):
+
+The Creator does not sufficiently understand the task. Do not spawn Maker.
+
+1. Emit decision event with `"chosen":"pause"`
+2. Display message to user: "Creator rated task understanding at <score>. Clarification needed before proceeding."
+3. Block until the user provides clarification
+4. Re-run Creator with the clarification appended to the task description
 
-If A3 triggers, emit a `decision` event:
 ```bash
 ./lib/archeflow-event.sh "$RUN_ID" decision plan "" \
-  '{"what":"confidence_gate","chosen":"<action>","rationale":"<axis> scored <score>"}' "$SEQ_CREATOR_COMPLETE"
+  '{"what":"confidence_gate","chosen":"pause","rationale":"task_understanding scored '"$TASK_UNDERSTANDING"'"}' "$SEQ_CREATOR_COMPLETE"
 ```
 
+**Upgrade branch** (Solution completeness < 0.5):
+
+The Creator's proposal is incomplete — more research is needed.
+
+1. If fast workflow: upgrade to standard, spawn Explorer, then re-run Creator with Explorer output
+2. If already standard/thorough: re-run Explorer with a focused prompt targeting the incomplete areas
+
+```bash
+./lib/archeflow-event.sh "$RUN_ID" decision plan "" \
+  '{"what":"confidence_gate","chosen":"upgrade","rationale":"solution_completeness scored '"$SOLUTION_COMPLETENESS"'"}' "$SEQ_CREATOR_COMPLETE"
+
+# If fast → standard upgrade:
+WORKFLOW="standard"
+# Spawn Explorer, then re-run Creator with Explorer findings
+```
+
+**Mini-Explorer branch** (Risk coverage < 0.5):
+
+The Creator identified risks but lacks confidence in their assessment. Spawn a focused Explorer to investigate.
+
+```
+Agent(
+  description: "Mini-Explorer: investigate risk area for <task>",
+  prompt: "You are the EXPLORER archetype. The Creator rated risk coverage at <score>.
+    Identified risks: <risks from plan-creator.md>
+    Research ONLY the risky areas. Answer: Is the risk real? What mitigations exist? What tests/guards would help?
+    Limit: focused output only.",
+  subagent_type: "Explore"
+)
+```
+
+Save output to `.archeflow/artifacts/${RUN_ID}/plan-mini-explorer.md`. The Maker receives both `plan-creator.md` and `plan-mini-explorer.md` as context.
+
+```bash
+./lib/archeflow-event.sh "$RUN_ID" decision plan "" \
+  '{"what":"confidence_gate","chosen":"mini_explorer","rationale":"risk_coverage scored '"$RISK_COVERAGE"'"}' "$SEQ_CREATOR_COMPLETE"
+```
+
+**Note:** The mini-Explorer runs in parallel with Do phase preparation (5 min max). The Maker can proceed once both `plan-creator.md` and `plan-mini-explorer.md` are available.
+
 #### 1d. Phase Transition: Plan to Do
 
 ```bash
@@ -184,6 +269,28 @@ After Maker returns:
 
 **Critical:** Verify the Maker committed its changes before proceeding. If uncommitted changes exist, instruct the Maker to commit.
 
+#### 2a-ii. Test-First Validation
+
+After Maker completes, check `do-maker-files.txt` for test files:
+```bash
+TEST_FILES=$(grep -iE '([/_.-](test|spec)[/_.-]|\.(test|spec)\.|_(test|spec)\.|/tests?/|/__tests__/|/specs?/)' ".archeflow/artifacts/${RUN_ID}/do-maker-files.txt" || true)
+```
+
+If `TEST_FILES` is empty and domain is not `writing`:
+1. Check if `plan-creator.md` contains a `### Test Strategy` section
+2. If yes: re-run Maker with targeted test instruction (one retry within Do phase)
+3. If no test strategy specified: emit WARNING event and proceed
+
+```bash
+./lib/archeflow-event.sh "$RUN_ID" decision do "" \
+  '{"what":"test_first_gate","chosen":"<pass|warn|retry>","rationale":"<reason>"}' "$SEQ_MAKER_COMPLETE"
+```
+
+The re-run prompt for the retry case:
+> "The proposal specified these test cases: <test strategy section>. No test files were found in your changes. Add the specified tests before finishing."
+
+This is one retry within the Do phase, not a full PDCA cycle. If the retry also produces no tests, emit WARNING and proceed to Check.
+
 #### 2b. Phase Transition: Do to Check
 
 ```bash
@@ -301,12 +408,46 @@ If all reviewers approved (and completion criteria met, if defined):
      '{"cycle":<N>,"max_cycles":<M>,"exit_condition":"all_approved","met":true,"next_action":"complete"}' "$SEQ_CHECK_TO_ACT"
    ```
 
-2. Run pre-merge hooks (check `.archeflow/hooks.yaml`)
+2. **Pre-merge hook check:**
-3. Merge Maker's worktree branch: `git merge --no-ff <branch>`
+   ```bash
-4. Run post-merge hooks + test suite
+   # Read hooks config if it exists
-   - Tests pass → continue
+   if [[ -f ".archeflow/hooks.yaml" ]]; then
-   - Tests fail → auto-revert, cycle back with "integration test failure" feedback
+     PRE_MERGE_HOOKS=$(grep -A5 "pre-merge:" .archeflow/hooks.yaml || true)
-5. Clean up worktree
+     if [[ -n "$PRE_MERGE_HOOKS" ]]; then
+       echo "Running pre-merge hooks..."
+       # Execute hooks; abort merge if fail_action: abort
+       # Hook execution is project-specific — see .archeflow/hooks.yaml
+     fi
+   fi
+   ```
+
+3. **Merge the Maker's worktree branch:**
+   ```bash
+   ./lib/archeflow-git.sh merge "$RUN_ID" --no-ff
+   ```
+
+4. **Post-merge test validation** (using the auto-rollback script):
+   ```bash
+   # Run tests and auto-revert if they fail
+   if ! ./lib/archeflow-rollback.sh "$RUN_ID"; then
+     # Rollback script already reverted HEAD and emitted decision event
+     # If cycles remain, cycle back with integration test failure feedback
+     if [[ "$CYCLE" -lt "$MAX_CYCLES" ]]; then
+       echo "Cycling back with integration test failure feedback..."
+       # Build act-feedback.md with "integration test failure on main" as top finding
+       # Continue to step 4d (Issues Found)
+     else
+       echo "Max cycles reached. Reporting failure to user."
+       # Continue to step 4e (Max Cycles Reached)
+     fi
+   fi
+   ```
+
+5. **Clean up worktree:**
+   ```bash
+   ./lib/archeflow-git.sh cleanup "$RUN_ID"
+   ```
+
 6. Proceed to Completion (step 5)
 
 #### 4d. Branch: Issues Found (cycles remaining)