devflow-kit 3.5.0 → 3.6.0

package/src/assets/commands/resolve.mds

@@ -122,7 +122,7 @@ Resolve this per worktree — unlike the evidence policy above, the settings lin
 
 {{compliance.compliance_inject()}}
 
-Set it per worktree, from that worktree's lens, and pass that worktree's `COMPLIANCE_DIRECTIVE` to each of its Code and Code-fix spawns, on a line of its own.
+Set it per worktree, from that worktree's lens, and pass that worktree's `COMPLIANCE_DIRECTIVE` to each of its Code and Fix spawns, on a line of its own.
 
 **Mint `RESOLUTION_TS` once per run:** `date -u +%Y-%m-%dT%H:%M:%SZ`. Every worktree reuses it — the resolution comment's dedup marker is searched per PR, so one run key keeps a retry of this run deduplicated while the next /resolve on the same PR posts. Phase 5 writes it as the summary's `**Date**:` and Phase 9b-2 passes it, so the local file and the posted marker agree.
 
@@ -274,7 +274,7 @@ Collect from each Code agent:
 **Produces:** RESOLUTION_FILE (early write for compaction safety)
 **Requires:** TRIAGE_RESULTS, CODE_AGENT_RESULTS, TARGET_DIR, TARGET_DIR_REL, BRANCH_INFO, RESOLUTION_TS
 
-**Immediately write `resolution-summary.md`** to `{TARGET_DIR}` using the Write tool. Do this now — not in Phase 9 — while results are fresh in context. This ensures the record is persisted even if later phases (Simplify, Verification Gate, CI gate, Tech Debt) trigger context compaction.
+**Immediately write `resolution-summary.md`** to `{TARGET_DIR}` using the Write tool. Do this now — not in Phase 9 — while results are fresh in context. This ensures the record is persisted even if later phases (Polish, Verification Gate, CI gate, Tech Debt) trigger context compaction.
 
 Set `Tracked` for FIX_SEPARATE and TECH_DEBT items to `(pending)` — to be backfilled after Phase 9 manage-debt (or `TRACEABILITY: DEGRADED ({reason})` if manage-debt degrades).
 
@@ -282,19 +282,19 @@ DUPLICATE issues are listed **only** in `## Duplicates` — never in `## Fixed I
 
 Use the template from the Output Artifact section below.
 
-### Phase 6: Simplify
+### Phase 6: Polish
 
-**Produces:** SIMPLIFICATION_RESULT
+**Produces:** POLISH_RESULT
 **Requires:** CODE_AGENT_RESULTS
 
-If any fixes were made, spawn Simplify agent to refine the changed code:
+If any fixes were made, spawn Polish agent to refine the changed code:
 
 ```
-Agent(subagent_type="Simplify", run_in_background=false):
+Agent(subagent_type="Polish", run_in_background=false):
 "TASK_DESCRIPTION: Issue resolution fixes
 WORKTREE_PATH: {worktree_path}  (omit if cwd)
 FILES_CHANGED: {list of files modified by Code agents}
-Simplify and refine the fixes for clarity and consistency
+Polish and refine the fixes for clarity and consistency
 Commit any improvements with a conventional-commit message."
 ```
 
@@ -320,9 +320,9 @@ Run build, typecheck, lint, test. Report pass/fail with failure details."
 1. Extract failure details from Validate agent output
 2. Increment `validation_retry_count`
 3. If `validation_retry_count <= 2`:
-   - Spawn Code-fix agent with fix context:
+   - Spawn Fix agent with fix context:
    ```
-   Agent(subagent_type="Code-fix"):
+   Agent(subagent_type="Fix"):
    "OPERATION: validation-fix
    TASK_ID: resolve-{batch-id}-valfix-{count}
    VALIDATION_FAILURES: {parsed failures from Validate agent}
@@ -342,7 +342,7 @@ Run build, typecheck, lint, test. Report pass/fail with failure details."
 Record `## Verification` outcome in resolution-summary.md (runs unconditionally after the validation loop exits):
 - Rewrite the `## Verification` section with | Command | Result | table + `Final gate: PASS | FAILED after N attempts`
 
-Push all commits to remote once (Code and Code-fix agents ran with PUSH: false — runs whether the gate PASSED or FAILED, so the branch is always visible before Phase 9 or CI runs):
+Push all commits to remote once (Code and Fix agents ran with PUSH: false — runs whether the gate PASSED or FAILED, so the branch is always visible before Phase 9 or CI runs):
 ```bash
 git -C {worktree} push
 ```
@@ -381,9 +381,9 @@ Phase 7 has pushed already, so this is a no-op unless the head moved since. `exi
 4. **If PENDING** and fewer than 3 waits have run → wait again (step 1). After the third wait → report "CI still running — verify manually before merging" and proceed.
 5. **If INDETERMINATE** and fewer than 3 waits have run → wait again (step 1). After the third wait → report "CI status unknown — verify manually before merging" and proceed.
 <!-- learning:on -->
-6. **If FAILING** and fewer than 2 fixes have run → report the failing checks from the line. Spawn `Agent(subagent_type="Code-fix")` whose prompt opens with `OPERATION: ci-fix`, with `COMPLIANCE_DIRECTIVE` (when it is not empty), `CI_FAILURES`, `DECISIONS_CONTEXT` and `PUSH: false`; `CI_FAILURES` holds the failing-check names from the line and nothing else, because the Code-fix agent fetches the full names and reads the logs itself and this command reads none. After a fix, push with the command above and, if a wait remains, wait again (step 1); a failed push records `TRACEABILITY: DEGRADED (ci push failed)`, reports "CI status unknown — verify manually before merging" and stops waiting. After the second fix still FAILING → report the failing checks and proceed.
+6. **If FAILING** and fewer than 2 fixes have run → report the failing checks from the line. Spawn `Agent(subagent_type="Fix")` whose prompt opens with `OPERATION: ci-fix`, with `COMPLIANCE_DIRECTIVE` (when it is not empty), `CI_FAILURES`, `DECISIONS_CONTEXT` and `PUSH: false`; `CI_FAILURES` holds the failing-check names from the line and nothing else, because the Fix agent fetches the full names and reads the logs itself and this command reads none. After a fix, push with the command above and, if a wait remains, wait again (step 1); a failed push records `TRACEABILITY: DEGRADED (ci push failed)`, reports "CI status unknown — verify manually before merging" and stops waiting. After the second fix still FAILING → report the failing checks and proceed.
 <!-- learning:off -->
-6. **If FAILING** and fewer than 2 fixes have run → report the failing checks from the line. Spawn `Agent(subagent_type="Code-fix")` whose prompt opens with `OPERATION: ci-fix`, with `COMPLIANCE_DIRECTIVE` (when it is not empty), `CI_FAILURES` and `PUSH: false`; `CI_FAILURES` holds the failing-check names from the line and nothing else, because the Code-fix agent fetches the full names and reads the logs itself and this command reads none. After a fix, push with the command above and, if a wait remains, wait again (step 1); a failed push records `TRACEABILITY: DEGRADED (ci push failed)`, reports "CI status unknown — verify manually before merging" and stops waiting. After the second fix still FAILING → report the failing checks and proceed.
+6. **If FAILING** and fewer than 2 fixes have run → report the failing checks from the line. Spawn `Agent(subagent_type="Fix")` whose prompt opens with `OPERATION: ci-fix`, with `COMPLIANCE_DIRECTIVE` (when it is not empty), `CI_FAILURES` and `PUSH: false`; `CI_FAILURES` holds the failing-check names from the line and nothing else, because the Fix agent fetches the full names and reads the logs itself and this command reads none. After a fix, push with the command above and, if a wait remains, wait again (step 1); a failed push records `TRACEABILITY: DEGRADED (ci push failed)`, reports "CI status unknown — verify manually before merging" and stops waiting. After the second fix still FAILING → report the failing checks and proceed.
 <!-- learning:end -->
 7. **Budget**: at most 3 waits and 2 fixes in all, per worktree. When one is spent, report the current status and proceed.
 <!-- /PATTERN: ci-status-gate -->
@@ -494,19 +494,13 @@ Capture the Git agent's `**Publication**:` and `**Status**:` lines as `PR_COMMEN
 
 **Step 9b-3: Refresh the test-plan evidence**
 
-Run this step only when Step 9b-0 ran — the head moved — and its `EVIDENCE` line did not read `total:0` with `exceptions:none` (nothing to record); otherwise record `EVIDENCE_REFRESH` as `SKIPPED ({reason})`. Spawn Git agent:
+Run this step only when Step 9b-0 ran — the head moved — and its `EVIDENCE` line did not read `total:0` with `exceptions:none` (nothing to record); otherwise record `EVIDENCE_REFRESH` as `SKIPPED ({reason})`. Run the script inline — it is the whole `update-pr-evidence` operation, with no Git agent spawn — through the Bash tool with `timeout: 180000`:
 
-```
-Agent(subagent_type="Git"):
-"OPERATION: update-pr-evidence
-PR_NUMBER: {pr_number}
-EVIDENCE_FILE: {TARGET_DIR_REL}/evidence.md
-REVIEW_PUBLICATION: {9b-2's publication mode}
-WORKTREE_PATH: {worktree_path}  (omit if cwd)
-Refresh the PR's test-plan block and post its evidence comment."
+```bash
+cd {worktree} && node "$HOME/.devflow/scripts/verify-evidence.cjs" publish --pr {pr_number} --evidence "{TARGET_DIR_REL}/evidence.md" --publication {9b-2's publication mode}; echo "exit=$?"
 ```
 
-Omit the `EVIDENCE_FILE` line when Step 9b-0 appended no claim. `REVIEW_PUBLICATION` is the mode 9b-2 reported on its `**Publication**:` line — `FULL…` → `full`, `STUB…` → `stub`, `OFF…` → `off` — else `{REVIEW_PUBLICATION}` as resolved in Step 0d. Capture its `EVIDENCE` line and its `**Body**:` / `**Comment**:` line, or its `TRACEABILITY: DEGRADED ({reason})` line, as `EVIDENCE_REFRESH`. It never blocks.
+Drop the `--evidence` pair when Step 9b-0 appended no claim. Run it only when `TARGET_DIR_REL` matches `^[A-Za-z0-9._/-]+$` — it carries the branch name, which a fork author picks — and `{pr_number}` is digits only; treat any other value as a failed run. The publication value is the mode 9b-2 reported on its `**Publication**:` line — `FULL…` → `full`, `STUB…` → `stub`, `OFF…` → `off` — else `{REVIEW_PUBLICATION}` as resolved in Step 0d. Capture its stdout as `EVIDENCE_REFRESH`: the `## PR Evidence` block's `EVIDENCE` line and its `**Body**:` / `**Comment**:` line, with any `TRACEABILITY: DEGRADED ({reason})` lines after them (exit 0), or the one line `TRACEABILITY: DEGRADED (evidence unavailable)` (exit 2). Empty stdout or any other exit is `TRACEABILITY: DEGRADED (evidence unavailable)`. It never blocks.
 
 ### Phase 9c: Merge Readiness (Report-only)
 
@@ -515,19 +509,17 @@ Omit the `EVIDENCE_FILE` line when Step 9b-0 appended no claim. `REVIEW_PUBLICAT
 
 Run this phase only when `REQUIRE_NON_AUTHOR_APPROVAL` is `true`; otherwise skip it and report it as SKIPPED.
 
-Spawn Git agent:
+Run the script inline — it is the whole `check-merge-readiness` operation, with no Git agent spawn — through the Bash tool with `timeout: 180000`:
 
+```bash
+cd {worktree} && node "$HOME/.devflow/scripts/verify-evidence.cjs" readiness --pr {pr_number} --require-non-author-approval true; echo "exit=$?"
 ```
-Agent(subagent_type="Git"):
-"OPERATION: check-merge-readiness
-PR_NUMBER: {pr_number}
-REQUIRE_NON_AUTHOR_APPROVAL: {REQUIRE_NON_AUTHOR_APPROVAL}
-WORKTREE_PATH: {worktree_path}  (omit if cwd)"
-```
+
+Pass `--require-non-author-approval true`: `REQUIRE_NON_AUTHOR_APPROVAL` is `true` here, or this phase would not run. `{pr_number}` is digits only. Its stdout is the `## Merge Readiness` block (exit 0), or the same block with `**Status**: DEGRADED ({reason})` and a `TRACEABILITY: DEGRADED ({reason})` line after it (exit 2); empty stdout or any other exit is `TRACEABILITY: DEGRADED (readiness unavailable)`.
 
 Include merge readiness verdict (READY / NOT_READY / DEGRADED) and its `- Test plan:` detail line in Phase 10 report. Never block on this result — report-only.
 
-If Git agent returns `TRACEABILITY: DEGRADED`: warn, proceed to Phase 10.
+If the script prints a `TRACEABILITY: DEGRADED` line: warn, proceed to Phase 10.
 
 ### Phase 10: Report
 
@@ -592,48 +584,24 @@ In multi-worktree mode, report results per worktree with aggregate summary.
 /resolve (orchestrator - spawns agents only)
 │
 ├─ Phase 0: Worktree Discovery & Pre-flight
-│  ├─ Step 0a: git worktree list → filter resolvable
-│  ├─ Step 0b: Git agent (validate-branch) per worktree [parallel] ← + DIFF_FILES
-│  ├─ Step 0c: Target latest review directory per worktree
-<!-- learning:on -->
-│  └─ Step 0d: Load project decisions → DECISIONS_CONTEXT + EVIDENCE_POLICY + REVIEW_PUBLICATION
-<!-- learning:off -->
-│  └─ Step 0d: Load project context → EVIDENCE_POLICY + REVIEW_PUBLICATION
-<!-- learning:end -->
-│
 ├─ Phase 1: Parse issues from TARGET_DIR + extract confidence %
-│
 ├─ Phase 1b: Fetch external threads (evidence policy required)
-│  └─ Git agent (fetch-review-threads) → THREAD_MAP
-│
 ├─ Phase 2: Global Triage [Triage agent, opus, single agent]
-│  └─ ALL issues → verdict ledger by disposition (incl. DUPLICATE with duplicate_of)
-│
 ├─ Phase 3: Batch FIX_NOW issues (skip if empty; DUPLICATE issues never dispatched)
-│  └─ same-file sequential, distinct-file parallel, max 5/batch
-│
 ├─ Phase 4: Fix [Code agent × N, OPERATION: issue-fix, PUSH: false]
-│  └─ Returns Verification block per batch
-│
 ├─ Phase 5: Write resolution-summary.md (compaction safety; Tracked = "(pending)" or "(pending — TRACEABILITY: DEGRADED)" if manage-debt degrades)
-│
-├─ Phase 6: Simplify [Simplify agent]
-│
-├─ Phase 7: Verification Gate [Validate agent, haiku] + push + Code-fix agent validation-fix loop ≤2
-│
+├─ Phase 6: Polish [Polish agent]
+├─ Phase 7: Verification Gate [Validate agent, haiku] + push + Fix agent validation-fix loop ≤2
 ├─ Phase 8: CI Status Gate (conditional — skipped if no fixes or verification FAILED)
-│  └─ push, then ci-wait.cjs (inline, one wait ≤ 570 s) → Code-fix agent on FAILING (3 waits + 2 fixes per worktree)
-│
 ├─ Phase 9: Git agent (manage-debt) — FIX_SEPARATE + TECH_DEBT → backfill Tracked={ISSUE_REF} (or TRACEABILITY: DEGRADED on failure)
-│  SEQUENTIAL across worktrees
 │
 ├─ Phase 9b: Thread resolution + resolution comment
 │  ├─ Step 9b-0: verify-evidence.cjs --stale-out → ≤1 Test agent on the stale TPs (wrapped) — only after this run's push
 │  ├─ Step 9b-1: Git agent (resolve-review-threads) — evidence policy required
 │  ├─ Step 9b-2: Git agent (post-resolution-summary, REVIEW_PUBLICATION) — always-on
-│  └─ Step 9b-3: Git agent (update-pr-evidence) — only when the head moved
+│  └─ Step 9b-3: verify-evidence.cjs publish (inline, no Git spawn) — only when the head moved
 │
-├─ Phase 9c: Git agent (check-merge-readiness) — non-author approval required, report-only
+├─ Phase 9c: verify-evidence.cjs readiness (inline, no Git spawn) — non-author approval required, report-only
 │
 └─ Phase 10: Display results (resolution-summary.md written in Phase 5)
 ```
@@ -647,21 +615,11 @@ In multi-worktree mode, report results per worktree with aggregate summary.
 | Fix attempt fails | Revert changes, mark BLOCKED, continue others |
 | Issue dependencies | Sequential chain, skip dependents if predecessor blocked |
 | No actionable issues | Report "No issues to resolve" |
-| Incomplete review directory (no review-summary.md) | Skip — resolve only targets complete reviews |
 | Latest review already resolved | Check bug-analysis fallback (Step 0c-5b); if also absent, skip worktree and suggest `/code-review` or `/bug-analysis` |
-| Legacy flat layout (no subdirectories) | Read flat *.md files directly (backwards compatible) |
 | `--review {timestamp}` in multi-worktree mode | Not supported — use `--path` + `--review` to target specific worktree + review |
-| Worktree pre-flight fails | Report failure, continue with other worktrees |
-| Empty FIX_NOW list | Skip Phases 3-4/6-8; still write full summary + run manage-debt if FIX_SEPARATE/TECH_DEBT exist |
-| ESCALATED security issues | Surfaced in ## Escalations + display callout; never routed to manage-debt |
-| DUPLICATE verdict without duplicate_of, or chained to another DUPLICATE | Treated as Triage failure — same retry-then-abort as a vanished id |
-| DUPLICATE issues in THREAD_MAP | Map ext-{N} to primary's verdict/verification status for thread reply |
-| Verification Gate FAILED after 2 attempts | Recorded as FAILED in ## Verification + blocking callout; CI gate skipped; proceed to Phase 9 (manage-debt) then Phase 10 (display) |
 | gh/GitHub absent | manage-debt degrades (`TRACEABILITY: DEGRADED ({reason})`); Tracked stays `(pending — TRACEABILITY: DEGRADED ({reason}))` — recorded, not dropped |
 | `EVIDENCE_POLICY` is `standard` | Phases 1b and 9b-step-1 are skipped; post-resolution-summary (Phase 9b step 2) still runs if a PR is known |
 | `REQUIRE_NON_AUTHOR_APPROVAL` is `false` | Phase 9c is skipped and reported as SKIPPED |
-| THREAD_MAP empty or DEGRADED | Phase 9b-1 skipped; resolution comment (Phase 9b-2) still posted if PR known |
-| No PR exists for post-resolution-summary | Git agent returns TRACEABILITY: DEGRADED; resolution-summary.md already on disk — not a blocker |
 | Public repo (`auto` mode) | Git agent probes visibility, posts counts-only STUB comment; full resolution report stays local |
 | `reviewPublication: off` | Git agent skips posting the resolution comment (OFF) — except that, only when `EVIDENCE_POLICY` is `required`, Step 0d passes `stub` and a counts-only STUB comment posts |
 | Fork PR this run cannot push to (no maintainer edits, no push access of its own) | validate-branch emits `TRACEABILITY: DEGRADED (cannot push to fork)` → `fork_no_push`: Phase 7 skips the push, Phase 8 is skipped, 9b-1 records FIXED threads as DEGRADED instead of citing unpushed commits; 9b-2 still posts the resolution comment; the head did not move, so 9b-0 and 9b-3 are skipped |
@@ -672,14 +630,8 @@ In multi-worktree mode, report results per worktree with aggregate summary.
 
 1. **Orchestration only** - Command spawns agents, doesn't do git/resolve work itself
 2. **No agent grades its own homework** - Triage agent validates, Code agents fix, Validate agent verifies
-3. **Global triage first** - Single Triage agent sees all issues for cross-issue consistency; no issue may vanish
-4. **Git agent for git work** - All git operations go through Git agent
-5. **Parallel execution** - Distinct-file Code agent batches run in parallel; same-file batches sequential
-6. **Honest reporting** - Verification failure is recorded and displayed, never silenced
-7. **Complete tracking** - Every issue gets exactly one verdict in the ledger
-8. **Latest review by default** - Only process the most recent complete review
-9. **Auto-discover worktrees** - One command handles all resolvable branches
-10. **Traceability-aware** - Policy-gated ops (thread fetch/resolve, merge readiness) are skipped cleanly when the evidence policy does not ask for them; resolution comment (Phase 9b-2) is always-on; test-plan evidence is re-verified (≤1 Test agent) and refreshed only when this run moved the head (Steps 9b-0, 9b-3)
+3. **Git agent for git work** - All git operations go through Git agent; the CI wait, the evidence refresh and the merge-readiness check are inline scripts (plumbing, no model work)
+4. **Traceability-aware** - Policy-gated ops (thread fetch/resolve, merge readiness) are skipped cleanly when the evidence policy does not ask for them; resolution comment (Phase 9b-2) is always-on; test-plan evidence is re-verified (≤1 Test agent) and refreshed only when this run moved the head (Steps 9b-0, 9b-3)
 
 ## Output Artifact
 

package/src/assets/commands/self-review.mds

@@ -1,5 +1,5 @@
 ---
-description: Self-review workflow - Simplify agent (code clarity) then Scrutinize agent (9-pillar quality gate)
+description: Self-review workflow - Polish agent (code clarity) then Harden agent (9-pillar quality gate)
 output-dir: dist/commands
 ---
 @import { knowledge_load, knowledge_writeback } from "./_partials/_knowledge.mds"
@@ -7,7 +7,7 @@ output-dir: dist/commands
 @import "./_partials/_settings.mds" as settings
 # Self-Review Command
 
-Run Simplify agent and Scrutinize agent sequentially on changed files for post-implementation quality refinement.
+Run Polish agent and Harden agent sequentially on changed files for post-implementation quality refinement.
 
 ## Usage
 
@@ -30,18 +30,18 @@ Detect changed files and build context:
 2. Else run `git diff --name-only HEAD` + `git diff --name-only --cached` to get staged + unstaged
 3. If no changes found, report "No changes to review" and exit
 4. Build TASK_DESCRIPTION from recent commit messages or branch name
-5. Record `HEAD_BEFORE` (`git rev-parse HEAD`) now, before Simplify runs — Phase 3 compares against it
+5. Record `HEAD_BEFORE` (`git rev-parse HEAD`) now, before Polish runs — Phase 3 compares against it
 
 {{settings.settings_resolve()}}
 
 {{decisions_load()}}
 <!-- learning:on -->
-Pass `DECISIONS_CONTEXT` to Scrutinize agent — the compact index lists active ADR/PF entries; Scrutinize agent uses `devflow:apply-decisions` to Read full entry bodies on demand. Known pitfalls help identify reintroduced issues, prior decisions help validate architectural consistency. (Simplify agent does not consume decisions — it operates at code-shape level and Scrutinize agent runs after to catch any architectural drift.)
+Pass `DECISIONS_CONTEXT` to Harden agent — the compact index lists active ADR/PF entries; Harden agent uses `devflow:apply-decisions` to Read full entry bodies on demand. Known pitfalls help identify reintroduced issues, prior decisions help validate architectural consistency. (Polish agent does not consume decisions — it operates at code-shape level and Harden agent runs after to catch any architectural drift.)
 
 <!-- learning:end -->
 {{knowledge_load()}}
 
-Pass `FEATURE_KNOWLEDGE_RULES` to Scrutinize agent.
+Pass `FEATURE_KNOWLEDGE_RULES` to Harden agent.
 
 <!-- learning:on -->
 **Extract:** FILES_CHANGED (list), TASK_DESCRIPTION (string), DECISIONS_CONTEXT (string, optional), FEATURE_KNOWLEDGE (string, optional), FEATURE_KNOWLEDGE_RULES (string, optional), HEAD_BEFORE (40-hex SHA)
@@ -49,33 +49,33 @@ Pass `FEATURE_KNOWLEDGE_RULES` to Scrutinize agent.
 **Extract:** FILES_CHANGED (list), TASK_DESCRIPTION (string), FEATURE_KNOWLEDGE (string, optional), FEATURE_KNOWLEDGE_RULES (string, optional), HEAD_BEFORE (40-hex SHA)
 <!-- learning:end -->
 
-### Phase 1: Simplify agent (Code Refinement)
+### Phase 1: Polish agent (Code Refinement)
 
-**Produces:** SIMPLIFY_COMMITS
+**Produces:** POLISH_COMMITS
 **Requires:** FILES_CHANGED, TASK_DESCRIPTION
 
-Spawn Simplify agent to refine code for clarity and consistency:
+Spawn Polish agent to refine code for clarity and consistency:
 
-Agent(subagent_type="Simplify", run_in_background=false):
+Agent(subagent_type="Polish", run_in_background=false):
 "TASK_DESCRIPTION: {task_description}
 FILES_CHANGED: {files_changed}
-Simplify and refine the code for clarity and consistency while preserving functionality.
+Polish and refine the code for clarity and consistency while preserving functionality.
 Commit any improvements with a conventional-commit message."
 
-**Wait for completion.** Simplify agent commits changes directly.
+**Wait for completion.** Polish agent commits changes directly.
 
-### Phase 2: Scrutinize agent (9-Pillar Quality Gate)
+### Phase 2: Harden agent (9-Pillar Quality Gate)
 
-**Produces:** SCRUTINIZE_STATUS
+**Produces:** HARDEN_STATUS
 <!-- learning:on -->
 **Requires:** FILES_CHANGED, TASK_DESCRIPTION, DECISIONS_CONTEXT
 <!-- learning:off -->
 **Requires:** FILES_CHANGED, TASK_DESCRIPTION
 <!-- learning:end -->
 
-Spawn Scrutinize agent for quality evaluation and fixing:
+Spawn Harden agent for quality evaluation and fixing:
 
-Agent(subagent_type="Scrutinize", run_in_background=false):
+Agent(subagent_type="Harden", run_in_background=false):
 "TASK_DESCRIPTION: {task_description}
 FILES_CHANGED: {files_changed}
 <!-- learning:on -->
@@ -93,11 +93,11 @@ Follow devflow:apply-feature-knowledge for FEATURE_KNOWLEDGE. Skip if (none)."
 ### Phase 3: Conditional Validation
 
 **Produces:** VALIDATION_RESULT
-**Requires:** HEAD_BEFORE, SCRUTINIZE_STATUS
+**Requires:** HEAD_BEFORE, HARDEN_STATUS
 
 If STATUS is BLOCKED, skip this phase: the report (Phase 4) names the blocker.
 
-Run this phase only if HEAD moved — `git rev-parse HEAD` differs from `HEAD_BEFORE`, meaning Simplify or Scrutinize committed (Simplify alone counts, whatever Scrutinize's STATUS is). Otherwise skip it. Its scope is changed-only over what the two agents changed:
+Run this phase only if HEAD moved — `git rev-parse HEAD` differs from `HEAD_BEFORE`, meaning Polish or Harden committed (Polish alone counts, whatever Harden's STATUS is). Otherwise skip it. Its scope is changed-only over what the two agents changed:
 
 Agent(subagent_type="Validate", run_in_background=false):
 "FILES_CHANGED: {output of `git diff --name-only HEAD_BEFORE..HEAD`}
@@ -109,7 +109,7 @@ Run build, typecheck, lint, test on modified files"
 
 ### Phase 4: Report
 
-**Requires:** SCRUTINIZE_STATUS, VALIDATION_RESULT
+**Requires:** HARDEN_STATUS, VALIDATION_RESULT
 
 Display summary:
 
@@ -118,10 +118,10 @@ Display summary:
 **Files Reviewed**: {n}
 **Status**: {PASS|FIXED|BLOCKED}
 
-### Simplify agent
+### Polish agent
 - {n} files refined for clarity
 
-### Scrutinize agent (9-Pillar Evaluation)
+### Harden agent (9-Pillar Evaluation)
 | Pillar | Status |
 |--------|--------|
 | Design | {status} |
@@ -154,14 +154,14 @@ Display summary:
 │  └─ Record HEAD_BEFORE
 <!-- learning:end -->
 │
-├─ Phase 1: Simplify agent
+├─ Phase 1: Polish agent
 │  └─ Code refinement (commits directly)
 │
-├─ Phase 2: Scrutinize agent
+├─ Phase 2: Harden agent
 │  └─ 9-pillar quality gate (may fix and commit)
 │
 ├─ Phase 3: Validate agent (conditional)
-│  └─ If HEAD moved since HEAD_BEFORE (Simplify or Scrutinize committed), changed-only Validate over HEAD_BEFORE..HEAD
+│  └─ If HEAD moved since HEAD_BEFORE (Polish or Harden committed), changed-only Validate over HEAD_BEFORE..HEAD
 │
 └─ Phase 4: Report
    └─ Display summary with pillar status
@@ -171,15 +171,15 @@ Display summary:
 | Case | Handling |
 |------|----------|
 | No changes | Report "No changes to review" and exit |
-| Simplify agent finds nothing | Normal, continue to Scrutinize agent |
-| Scrutinize agent BLOCKED | Report blocking issue, halt workflow |
+| Polish agent finds nothing | Normal, continue to Harden agent |
+| Harden agent BLOCKED | Report blocking issue, halt workflow |
 | Validation fails | Report failures, halt (don't create broken state) |
 | Not in git repo | Report error, suggest running in git repo |
 
 ## Principles
 
 1. **Orchestration only** - Command spawns agents, doesn't do the work
-2. **Sequential execution** - Simplify agent must complete before Scrutinize agent
-3. **Validation gate** - If Simplify agent or Scrutinize agent committed, the changes must pass validation
+2. **Sequential execution** - Polish agent must complete before Harden agent
+3. **Validation gate** - If Polish agent or Harden agent committed, the changes must pass validation
 4. **Honest reporting** - Display actual agent outputs
 5. **Fail fast** - Stop on BLOCKED or validation failure

package/src/assets/mds/git/_pr.mds

@@ -260,6 +260,8 @@ Load for `check-merge-readiness` under every tracker provider.
 
 ### Process
 
+Run the script from `WORKTREE_PATH` (else cwd) and print its stdout, nothing else: `node "$HOME/.devflow/scripts/verify-evidence.cjs" readiness --pr {PR_NUMBER}; echo "exit=$?"`, adding `--require-non-author-approval {REQUIRE_NON_AUTHOR_APPROVAL}` only when that is `true` or `false`, with the Bash `timeout` at 180000. On exit 0 or 2 its stdout is the `## Merge Readiness` block (exit 2: `DEGRADED`, closed by a `TRACEABILITY: DEGRADED ({reason})` line); any other exit, or empty stdout, is `TRACEABILITY: DEGRADED (readiness unavailable)`. The script makes the reads and applies the ladder below, so the steps are its specification: run none of them yourself.
+
 1. Fetch unresolved review threads via GraphQL: `reviewThreads(first: 100) { nodes { isResolved } totalCount }`. Count unresolved from nodes (`isResolved == false`). If `totalCount > 100`, report the unresolved count as approximate: prefix with `>` and note `(count approximate — PR has more than 100 threads)`.
 2. Fetch PR review decision: `gh pr view {PR_NUMBER} --json reviewDecision --jq '.reviewDecision'`
    - Values: `APPROVED`, `CHANGES_REQUESTED`, `REVIEW_REQUIRED`, or null
@@ -289,16 +291,14 @@ Never take action on the PR — report READY or NOT_READY, always with the speci
 
 Load for `update-pr-evidence` under every tracker provider.
 
-**PR mechanics held here:** the evidence script run, the compare-and-swap body edit and the append-only evidence comment. The script owns every marker, grammar and state rule; nothing here restates one.
+**PR mechanics held here:** the one script run. `verify-evidence.cjs publish` owns every step, marker, grammar and state rule, and scrubs (D11) each body before it posts one; nothing here restates any of them.
 
 ### Process
 
-Run steps 1–4 as ONE Bash invocation from `WORKTREE_PATH` (else cwd) — the trap removes `$S` and the temp files when it exits — with `V="$HOME/.devflow/scripts"`.
+1. From `WORKTREE_PATH` (else cwd), run `node "$HOME/.devflow/scripts/verify-evidence.cjs" publish --pr {PR_NUMBER}; echo "exit=$?"`, adding `--publication {REVIEW_PUBLICATION}` only when that is `auto`, `full`, `off` or `stub`, and `--evidence "{EVIDENCE_FILE}"` when given — only a value matching `^[A-Za-z0-9._/-]{1,255}$` reaches the shell; any other is a failed run. Set the Bash `timeout` to 180000.
+2. Print the script's stdout and nothing else. On exit 0 it is the `## PR Evidence` block: the heading, the line `EVIDENCE pr:<n> head:<sha> total:<n> VERIFIED-CI:<n> ATTESTED-LOCAL:<n> UNVERIFIED:<n> STALE:<n> FAILED:<n> INDETERMINATE:<n> stale:<ids|none> exceptions:<kinds|none> approval:<yes|no|unchecked> key:<hex> posted:<yes|no|n/a> body:<same|changed>`, and the `**Body**:` / `**Comment**:` line, then one `TRACEABILITY: DEGRADED ({reason})` line for each part that degraded, such as `DEGRADED (concurrent edit)` (the body edit then reads `SKIPPED`), `DEGRADED (body read-back mismatch)` or `DEGRADED (redaction unavailable)`: a body the script cannot scrub is never posted. On exit 2 it is `TRACEABILITY: DEGRADED (evidence unavailable)`. Any other exit, or empty stdout, is a failed run: emit that same line.
 
-1. **Verify.** Set `S=`, arm the D11 trap with `[ -n "$S" ] && { rm -- "$S/base" "$S/base.sha256"; rmdir -- "$S"; } 2>/dev/null` added before its `exit`, then the four `mktemp`s and `S="$(mktemp -d)"`. Run `node "$V/verify-evidence.cjs" verify --pr {PR_NUMBER} --state "$S" --block-out "$DEVFLOW_NOTES_RAW" --comment-out "$DEVFLOW_BODY_RAW"`, adding `--publication {REVIEW_PUBLICATION}` only when that is `auto`, `full`, `off` or `stub`, and `--evidence "{EVIDENCE_FILE}"` when given — only a value matching `^[A-Za-z0-9._/-]{1,255}$` reaches the shell; any other is a failed run. Continue only on exit 0 with stdout exactly one line, `EVIDENCE pr:<n> head:<sha> total:<n> VERIFIED-CI:<n> ATTESTED-LOCAL:<n> UNVERIFIED:<n> STALE:<n> FAILED:<n> INDETERMINATE:<n> stale:<ids|none> exceptions:<kinds|none> approval:<yes|no|unchecked> key:<hex> posted:<yes|no|n/a> body:<same|changed>`; otherwise emit `TRACEABILITY: DEGRADED (evidence unavailable)` and stop. The script makes this op's one `gh pr view` read and prints nothing it read from the PR; never read the PR another way.
-2. **Body**, only on `body:changed` (else `UNCHANGED`): `node "$V/redact-secrets.cjs" "$DEVFLOW_NOTES_RAW" "$DEVFLOW_NOTES" && node "$V/verify-evidence.cjs" splice --pr {PR_NUMBER} --state "$S" --block "$DEVFLOW_NOTES" --out "$DEVFLOW_BODY" && gh pr edit {PR_NUMBER} --body-file "$DEVFLOW_BODY"`. Only the composed block is scrubbed (D11); every byte outside its markers is the PR's own and stays identical. `splice` re-reads the body: unchanged since step 1 → it writes; changed → it splices once onto the fresh body and re-reads; changed again → `SPLICE conflict`: `SKIPPED` and `TRACEABILITY: DEGRADED (concurrent edit)`. Any other non-zero → `DEGRADED ({reason})`, naming a printed `SPLICE` token. No edit either way; go to step 4.
-3. **Read back** after an edit: `node "$V/verify-evidence.cjs" readback --pr {PR_NUMBER} --expect "$DEVFLOW_BODY"`; anything but `READBACK ok` → `TRACEABILITY: DEGRADED (body read-back mismatch)`, else `EDITED`. GitHub has no conditional body edit: a human edit landing between the last re-read and `gh pr edit` is overwritten (it stays in the PR's edit history), and the read-back proves only that these bytes landed.
-4. **Comment.** `posted:yes` → `SKIPPED`; `posted:n/a` → `OFF`. Otherwise apply the Comment-sink scrub (D11): `node "$V/redact-secrets.cjs" "$DEVFLOW_BODY_RAW" "$DEVFLOW_BODY" && gh pr comment {PR_NUMBER} --body-file "$DEVFLOW_BODY"` → `POSTED`. Never edit or delete an evidence comment. On 5xx retry once; still 5xx → `DEGRADED ({reason})`.
+Run nothing else: the script makes the one PR read, the compare-and-swap body edit, its read-back and the append-only comment itself, and posts nothing it could not scrub.
 @end
 
 <!-- op: validate-branch -->

package/src/assets/scripts/hooks/assets/orchestrator-charter.md

@@ -5,16 +5,17 @@ Never do work-product mainline: no file edits, no builds, no multi-file reads, n
 
 Routing (Agent tool) — pick the roster agent that fits the work:
 - Search and listing: Explore. Codebase orientation: Skim.
-- Execution against a spec: Code (write code to a plan; open the prompt with `OPERATION: <mode>` — `issue-fix` for pre-classified review issues, else `implement`), Code-edit (mechanical changes: renames, moves, boilerplate; `OPERATION: edit`), Validate (build, typecheck, lint, test), Git (git/GitHub operations).
+- Execution against a spec: Code (write code to a plan; open the prompt with `OPERATION: <mode>` — `issue-fix` for pre-classified review issues, else `implement`), Refactor (a given mechanical change: "rename X to Y everywhere", moves, boilerplate; `OPERATION: edit`), Polish (judgment pass for clarity that keeps behaviour: "make this code cleaner"), Validate (build, typecheck, lint, test), Git (git/GitHub).
+- Bug fix: Code (`OPERATION: implement`; `issue-fix` only for Triage-classified review issues). Fix: gate failures only (`validation-fix`, `alignment-fix`, `qa-fix`, `ci-fix`).
 - Analysis, design, research: Design, Research, Review, Triage (validate review issues against blast-radius matrix).
-- Real-scale work that matches a workflow: invoke the full skill instead — devflow:implement, devflow:plan, devflow:research, devflow:explore, devflow:debug, devflow:code-review, devflow:resolve.
+- Real-scale work matching a workflow: invoke the full skill instead — devflow:implement, devflow:plan, devflow:research, devflow:explore, devflow:debug (all debug work, never the Debug agent), devflow:code-review, devflow:resolve.
 - Anything else: the closest roster agent, never general-purpose.
 
 Stays mainline (judgment work): conversation, decisions, routing, synthesizing agent reports, answers already in loaded context, one targeted Read to scope a delegation.
 
 Operating rules:
 - Decompose mainline. Subagents cannot spawn subagents — you own task breakdown, then delegate leaf tasks.
-- Subagents see none of this conversation. Make every delegation self-contained: goal, constraints, relevant session decisions and facts, exact paths. A deliverable that draws on the conversation (issue, PR, report) needs the substance in the prompt — not a pointer to it.
+- Subagents see none of this conversation. Make every delegation self-contained: goal, constraints, relevant session decisions and facts, exact paths. A deliverable that draws on the conversation (issue, PR, report) needs its substance in the prompt, not a pointer.
 - Report cap: ask every direct delegation for a final report of at most about 1,500 tokens — findings, paths and verdicts, not file dumps.
 - Parallelize independent delegations in one message. Git operations stay sequential.
 - Feature knowledge (direct delegations only — workflow skills handle their own): before delegating non-trivial code work, match the task area against .devflow/features/index.md and pass each matching KB's one to three most relevant `## Rules` bullets (verbatim, IDs included; a KB without Rules: Anti-Patterns or Gotchas entries, cited by section), its path and its `##` heading index as FEATURE_KNOWLEDGE; after delegated changes to a covered area, spawn Knowledge to refresh that KB.

package/src/assets/scripts/hooks/capture-prompt

@@ -43,7 +43,7 @@ df_resolve_roots "$CWD" 2>/dev/null || true
 PROJECT_ROOT="${DF_ROOT:-$CWD}"
 # The learning queue is the repository's, not the checkout's: in a linked worktree
 # it is the main worktree's queue (D-LEDGER-MAIN-WORKTREE, resolve-project-root),
-# the one the Learning agent drains into the shared ledger. Memory stays per checkout.
+# the one the Curate agent drains into the shared ledger. Memory stays per checkout.
 LEDGER_ROOT="${DF_LEDGER_ROOT:-$PROJECT_ROOT}"
 
 # The machine-wide manifest (the memory/learning switches, D-FEATURES-NARROW-ONLY

package/src/assets/scripts/hooks/capture-question

@@ -62,7 +62,7 @@ df_resolve_roots "$CWD" 2>/dev/null || true
 PROJECT_ROOT="${DF_ROOT:-$CWD}"
 # The learning queue is the repository's, not the checkout's: in a linked worktree
 # it is the main worktree's queue (D-LEDGER-MAIN-WORKTREE, resolve-project-root),
-# the one the Learning agent drains into the shared ledger. Memory stays per checkout.
+# the one the Curate agent drains into the shared ledger. Memory stays per checkout.
 LEDGER_ROOT="${DF_LEDGER_ROOT:-$PROJECT_ROOT}"
 
 # The machine-wide manifest (the memory/learning switches, D-FEATURES-NARROW-ONLY

package/src/assets/scripts/hooks/capture-turn

@@ -47,7 +47,7 @@ df_resolve_roots "$CWD" 2>/dev/null || true
 PROJECT_ROOT="${DF_ROOT:-$CWD}"
 # The learning queue is the repository's, not the checkout's: in a linked worktree
 # it is the main worktree's queue (D-LEDGER-MAIN-WORKTREE, resolve-project-root),
-# the one the Learning agent drains into the shared ledger. Memory stays per checkout.
+# the one the Curate agent drains into the shared ledger. Memory stays per checkout.
 LEDGER_ROOT="${DF_LEDGER_ROOT:-$PROJECT_ROOT}"
 
 # The machine-wide manifest (the memory/learning switches, D-FEATURES-NARROW-ONLY

package/src/assets/scripts/hooks/json-helper.cjs

@@ -2,9 +2,9 @@
 
 // src/assets/scripts/hooks/json-helper.cjs
 // Provides jq-equivalent operations for hooks when jq is not installed, and the
-// learning ops the Learning agent runs from the project root.
+// learning ops the Curate agent runs from the project root.
 // SECURITY: This is a local CLI helper invoked only by shell hooks and the
-// Learning agent with controlled arguments. No operation takes a file path: a
+// Curate agent with controlled arguments. No operation takes a file path: a
 // file's content arrives on stdin (json-parse redirects it), and the learning ops
 // build every path from the current directory.
 // Usage: node json-helper.cjs <operation> [args...]

package/src/assets/scripts/hooks/lib/learning-store.cjs

@@ -1516,7 +1516,7 @@ function moveQueueToClaim(queuePath, claimPath) {
 }
 
 /**
- * Claim the learning queue for one Learning run.
+ * Claim the learning queue for one Curate run.
  *
  * D-OWNED-CLAIM: the learning queue is claimed and released only through the
  * claim-queue and release-claim ops, under the learning lock. A claim moves the

package/src/assets/scripts/hooks/lib/project-paths.cjs

@@ -57,7 +57,7 @@ function getLearningPendingTurnsPath(projectRoot) {
   return path.join(projectRoot, '.devflow', 'learning', '.pending-turns.jsonl');
 }
 
-/** .devflow/learning/.pending-turns.processing — the claimed batch a Learning run holds while it processes it */
+/** .devflow/learning/.pending-turns.processing — the claimed batch a Curate run holds while it processes it */
 function getLearningPendingTurnsProcessingPath(projectRoot) {
   return path.join(projectRoot, '.devflow', 'learning', '.pending-turns.processing');
 }
@@ -81,8 +81,8 @@ function getPitfallsFilePath(projectRoot) {
   return path.join(projectRoot, '.devflow', 'learning', 'pitfalls.md');
 }
 
-/** .devflow/learning/learning.json — project-level learning agent tuning config */
-function getLearningTuningConfigPath(projectRoot) {
+/** .devflow/learning/learning.json — project-level curate agent tuning config */
+function getCurateTuningConfigPath(projectRoot) {
   return path.join(projectRoot, '.devflow', 'learning', 'learning.json');
 }
 
@@ -179,7 +179,7 @@ module.exports = {
   // Learning content files
   getDecisionsFilePath,
   getPitfallsFilePath,
-  getLearningTuningConfigPath,
+  getCurateTuningConfigPath,
   getDecisionsLedgerPath,
   getDecisionsLogPath,
   getDecisionsArchivePath,

package/src/assets/scripts/hooks/preamble

@@ -75,7 +75,7 @@ elif [[ "$HEAD" == "/"* ]]; then
   dbg "EXIT: slash command — no reminder"
 else
   dbg "ORCHESTRATOR_REMINDER injected"
-  json_prompt_output "Orchestrator reminder: coordinate, don't produce — delegate edits, builds, multi-file reads, and debug loops to the fitting roster agent (Agent tool) or the matching devflow workflow skill.
+  json_prompt_output "Orchestrator reminder: coordinate, don't produce — delegate edits, builds and multi-file reads to the fitting roster agent (Agent tool) or the matching devflow workflow skill. Send debug work to the devflow:debug skill, never to the Debug agent.
 Keep only judgment work mainline: conversation, decisions, routing, synthesis of agent reports."
 fi