ultimate-pi 0.22.0 → 0.22.2

package/.agents/skills/harness-context/SKILL.md

@@ -8,7 +8,7 @@ description: Compile task-specific harness context using context-mode and graphi
 ## When to use
 
 - Preparing context for `/harness-plan`, `/harness-run`, or `/harness-auto`
-- Navigating harness-related code and ADRs without reading entire repos
+- Navigating harness-related code and governance decisions without reading entire repos
 
 ## Mandatory: context-mode only
 
@@ -25,7 +25,7 @@ Use these in rough priority order — not every tool on every task:
 | Structural code patterns | `sg -p '…'` (ast-grep) |
 | Semantic implementation search | `ccc search` (harness pre-indexes before subprocess spawns) |
 | File detail | context-mode maps/signatures, then targeted reads |
-| Harness governance | `.pi/harness/docs/adrs/README.md` |
+| Harness governance | approved policies and decision logs in the target project |
 
 For `/harness-plan` Phase 1, parent compiles findings into `artifacts/planning-context.yaml` — see **harness-plan** skill.
 
@@ -33,7 +33,7 @@ For `/harness-plan` Phase 1, parent compiles findings into `artifacts/planning-c
 
 Compact context block:
 
-- Relevant ADRs (ids + one-line decision)
+- Relevant governance decisions (id/title + one-line decision)
 - Extension entry points (policy-gate, trace-recorder, harness-telemetry)
 - Schema versions in play
 

package/.agents/skills/harness-debate-plan/SKILL.md

@@ -5,7 +5,7 @@ description: Plan-phase Review Gate debate — pi-messenger threads, lane YAML,
 
 # harness-debate-plan
 
-**Practice map:** `.pi/harness/docs/practice-map.md` (Review Gate RACI).
+Review Gate RACI: parent is chair; lane agents provide structured evidence in sequence.
 
 Use when running **Phase 5** of `/harness-plan` — **Fagan-style structured inspection** per focus (`spec` | `wbs` | `schedule` | `quality`). Parent is **chair**; within-round dialogue (claims → rebuttals → clarifications → counters → integrate).
 
@@ -78,4 +78,4 @@ Resume: `harness_debate_round_status({ round_index: N })` → run listed `next_t
 
 Do not `approve_plan` on `policy_decision: block`. On `human_required` → `ask_user` first.
 
-Rubrics: `.pi/harness/docs/planning-rubrics.md`.
+Rubrics: use the focus-specific checklist ids passed by the parent for the active round.

package/.agents/skills/harness-decisions/SKILL.md

@@ -67,7 +67,7 @@ Use during **`/harness-plan` Phase 0** only. Purpose: disambiguate the **task**
   "options": [
     { "title": "Harness contract only", "description": "Changes under .pi/harness and prompts; harness-verify passes" },
     { "title": "End-to-end feature", "description": "User-visible behavior + tests in the app repo" },
-    { "title": "Docs / ADR only", "description": "No runtime code changes" }
+    { "title": "Docs / decision-record only", "description": "No runtime code changes" }
   ],
   "allowFreeform": true
 }
@@ -94,7 +94,7 @@ Use **`questions[]`** when ≥2 independent dimensions must be resolved together
 ```json
 {
   "question": "Lock the task contract before reconnaissance",
-  "context": "Phase 0 (ADR 0053). Answer both forks to set scope and acceptance.",
+  "context": "Phase 0 task-clarification gate. Answer both forks to set scope and acceptance.",
   "questions": [
     {
       "title": "Scope surface",

package/.agents/skills/harness-eval/SKILL.md

@@ -9,4 +9,4 @@ description: >-
 
 Use **`harness-review`** skill and **`/harness-review`** instead.
 
-The master command runs benchmark + policy verdict (+ adversary unless `--quick`) with `submit_eval_verdict` / `submit_adversary_report` and parent `harness_artifact_ready` gates (ADR 0037, ADR 0039).
+The master command runs benchmark + policy verdict (+ adversary unless `--quick`) with `submit_eval_verdict` / `submit_adversary_report` and parent `harness_artifact_ready` gates.

package/.agents/skills/harness-git-commit/SKILL.md

@@ -67,6 +67,6 @@ Edit project file to change format or co-author for external repos.
 
 ## References
 
-- ADR 0055 — `.pi/harness/docs/adrs/0055-auto-commit-coauthor-lifecycle.md`
+- Auto-commit lifecycle policy: use bootstrap + commit CLI so co-author and message format stay consistent.
 - Scripts — `harness-git-commit.mjs`, `harness-auto-commit-bootstrap.mjs`
 - Library — `.pi/lib/harness-auto-commit-config.mjs`

package/.agents/skills/harness-governor/SKILL.md

@@ -14,10 +14,10 @@ description: Enforce harness governance phases, policy gates, budgets, and promo
 ## Workflow
 
 1. Read current phase from `/harness-policy-status` or session `harness-policy-state`.
-2. Check ADRs: constitution (0001), eval promotion (0003), Sentrux (0006), drift (0007), rules lifecycle (0009), AGT policy (0046), AGT security layers (0047).
+2. Check governance policies: phase constitution, eval promotion rules, Sentrux requirements, drift handling, rules lifecycle, and AGT policy/security layers.
 3. Tool allow/deny is enforced by AGT `PolicyEngine` + `.pi/harness/policies/*.yaml` (parent `policy-gate`, subprocess `harness-subagent-governance`). Disable with `HARNESS_AGT_POLICY=0`. Audit: `.pi/harness/runs/<run_id>/agt-audit.jsonl`.
 4. For promotion: require eval pass, no abort lock, debate consensus if escalated, Sentrux when `HARNESS_SENTRUX_REQUIRED=true` (`artifacts/sentrux-signal.yaml` from `/harness-run`, not executor self-report).
-5. **Intent vs observation:** Sentrux manifest changes → `/harness-sentrux-steward` + chair + ADR when material, then `sentrux-rules-sync --force`. Naming manifest changes → `/harness-ls-lint-steward` + chair, then `ls-lint-rules-sync --force`. CLI degradation after execute → fix paths or replan — do not tune manifest on a single noisy run.
+5. **Intent vs observation:** Sentrux manifest changes → `/harness-sentrux-steward` + chair + formal decision record when material, then `sentrux-rules-sync --force`. Naming manifest changes → `/harness-ls-lint-steward` + chair, then `ls-lint-rules-sync --force`. CLI degradation after execute → fix paths or replan — do not tune manifest on a single noisy run.
 6. After approved Sentrux edits: `harness-sentrux-bootstrap.mjs --force` or `/harness-sentrux-sync`; emit `harness-architecture-changed`. After naming edits: `harness-ls-lint-bootstrap.mjs --force` or `/harness-ls-lint-sync`; emit `harness-naming-changed`.
 7. Run `node "$UP_PKG/.pi/scripts/harness-verify.mjs"` before claiming release readiness (includes AGT policy doctor).
 
@@ -30,13 +30,13 @@ When refining plans from noisy requirements:
 3. When gates return `human_required` or promotion is blocked, the orchestrator calls `ask_user` — do not guess scope.
 4. Reference graphify wiki or `graphify query` for architecture constraints before execute.
 
-## Budgets (ADR 0038)
+## Budgets
 
 - Default: **`HARNESS_BUDGET_ENFORCE` off** — token/debate caps are telemetry-only (`harness-budget-telemetry`, `harness-budget-soft-limit`). They do **not** block phases or debate lanes.
 - Do **not** skip reconnaissance artifacts (`planning-context.yaml`), debate rounds, or `approve_plan` because of soft budget hints in the widget.
 - Re-enable hard caps only with `HARNESS_BUDGET_ENFORCE=1` and `HARNESS_BUDGET_HARD_STOP` / `HARNESS_DEBATE_HARD_STOP`.
 
-## Subagent artifacts (ADR 0037)
+## Subagent artifacts
 
 - Subagents call scoped **`submit_*`** tools; parent verifies with **`harness_artifact_ready`**, not JSON parsing from `finalOutput`.
 - Parent **`write_harness_yaml`** is for merges (`research-brief.yaml`, plan shell) — not subagent payloads.
@@ -44,4 +44,4 @@ When refining plans from noisy requirements:
 ## Rules
 
 - Never auto-merge; harness-auto may open PR only when all gates pass (see release-readiness-report).
-- Do not invoke posthog-analyst in Phase 2 (ADR 0005).
+- Do not invoke posthog-analyst in Phase 2.

package/.agents/skills/harness-ls-lint-setup/SKILL.md

@@ -20,7 +20,7 @@ description: Bootstrap ls-lint filename rules for harness projects — seed nami
 | **Sync** | `ls-lint-rules-sync.mjs`, `/harness-ls-lint-sync` | Regenerates `.ls-lint.yml` from manifest after intent change |
 | **Observation** | `/harness-run`, `/harness-review` | `harness-ls-lint-cli.mjs` → `artifacts/ls-lint-signal.yaml` |
 
-Never auto-sync manifest from directory trees. Material manifest edits need steward evidence + chair approval (ADR 0052).
+Never auto-sync manifest from directory trees. Material manifest edits need steward evidence + chair approval.
 
 ## Canonical layout
 
@@ -54,6 +54,6 @@ Custom YAML **outside** `# --- harness:managed:start/end ---` is preserved on ev
 
 ## References
 
-- ADR 0052 — `.pi/harness/docs/adrs/0052-ls-lint-naming-lifecycle.md`
+- Naming lifecycle policy: steward proposal + chair approval before material manifest changes.
 - Scripts — `ls-lint-rules-sync.mjs`, `harness-ls-lint-bootstrap.mjs`, `harness-ls-lint-cli.mjs`
 - Agent — `harness/ls-lint-steward`

package/.agents/skills/harness-orchestration/SKILL.md

@@ -8,14 +8,14 @@ description: >-
 
 # Harness orchestration
 
-**Practice map:** `.pi/harness/docs/practice-map.md` · **ADR 0040** · **ADR 0041**.
+Follow the orchestration rules and phase sequence in this skill directly.
 
 ## Team management rules
 
 1. **Parallelism law** — Parallel `tasks` only when outputs are independent inputs to a later merge (implementation ∥ stack). Never parallelize debate lanes or decompose ∥ hypothesis.
 2. **Two-pizza cap per batch** — Max 2 research lanes, 1 optional `planning-context` subagent, 1 executor, 1 debate agent per `subagent` call.
 3. **No redundant thinkers** — Downstream agents read artifacts; do not re-derive.
-4. **Sequential dependency chain** — planning context → decompose → hypothesis → research → author → DAG → debate → approve → execute → **/harness-review** → optional **/harness-steer** loop (ADR 0044).
+4. **Sequential dependency chain** — planning context → decompose → hypothesis → research → author → DAG → debate → approve → execute → **/harness-review** → optional **/harness-steer** loop.
 5. **Path-first parent tools** — `approve_plan`, `create_plan`, `submit_*` via `source_path`, `merge_harness_yaml`, `harness_synthesize_repair_brief`.
 6. **Debate = meeting** — Parent is chair; parallel_probes allows evaluator ∥ adversary per batch.
 7. **Tool intelligence** — Parent uses graphify, sg, ccc, and reads by task need; subprocesses optional.
@@ -41,7 +41,7 @@ Harness subprocesses load **`harness-subagent-submit`** (`PI_HARNESS_SUBPROCESS=
 |---------|---------|
 | `/harness-plan` | Parent: planning context (tools) → decompose → hypothesis → Phase 3.5 artifacts → PlanPacket → eligibility + Review Gate → `approve_plan` + `create_plan` |
 | `/harness-run` | `harness/running/executor` (single worker) |
-| `/harness-review` | Parent verify → `evaluator` benchmark → `evaluator` verdict → `adversary` → optional `tie-breaker` (ADR 0039) |
+| `/harness-review` | Parent verify → `evaluator` benchmark → `evaluator` verdict → `adversary` → optional `tie-breaker` |
 | `/harness-eval` | **Deprecated** → `/harness-review` |
 | `/harness-critic` | **Deprecated** → `/harness-review` |
 | `/harness-auto` | plan per `/harness-plan`; `--quick` skips adversary + tie-breaker in review |
@@ -80,5 +80,5 @@ Then execution-plan-author, DAG gate, debate eligibility, sequential debate roun
 
 ## References
 
-- ADR 0032, ADR 0033, ADR 0040, ADR 0041, `.pi/harness/specs/harness-spawn-context.schema.json`
+- Subagent isolation, submit-tool artifact flow, and spawn-context contract: `.pi/harness/specs/harness-spawn-context.schema.json`
 - `node "$UP_PKG/.pi/scripts/harness-agents-manifest.mjs" --check`

package/.agents/skills/harness-plan/SKILL.md

@@ -5,7 +5,7 @@ description: Agent-native harness plans — lakes/context bundles, planning cont
 
 # harness-plan
 
-**Practice map:** `.pi/harness/docs/practice-map.md` · **ADR 0040** · **ADR 0042** · **ADR 0043**.
+Use this skill's phase order, spawn laws, and artifact contract directly.
 
 ## When to use
 
@@ -21,7 +21,7 @@ description: Agent-native harness plans — lakes/context bundles, planning cont
 
 ## Workflow (parent orchestrator)
 
-1. **Phase 0:** `artifacts/task-clarification.yaml` — investigate (code + web OK), `ask_user` until unambiguous, gate before any planning subagent (**ADR 0053**).
+1. **Phase 0:** `artifacts/task-clarification.yaml` — investigate (code + web OK), `ask_user` until unambiguous, gate before any planning subagent.
 2. **Phase 1:** Compile `artifacts/planning-context.yaml` with tools (default) or optional `planning-context` subagent; inherit Phase 0 grounding.
 3. **Sequential** decompose → gate `artifacts/decomposition.yaml`.
 4. **Sequential** hypothesis (requires decomposition).

package/.agents/skills/harness-review/SKILL.md

@@ -9,7 +9,7 @@ description: >-
 
 # harness-review
 
-**Practice map:** `.pi/harness/docs/practice-map.md` (Monitoring and Controlling: measure → judge → red team).
+Monitoring and Controlling flow: measure → judge → red team.
 
 ## When to use
 
@@ -42,7 +42,7 @@ Pass `sentrux-signal.yaml` path to evaluator `mode: benchmark` spawn context. Ev
 
 ## Rules
 
-- Parent never writes eval/adversary YAML — subprocess `submit_*` only (ADR 0037).
+- Parent never writes eval/adversary YAML — subprocess `submit_*` only.
 - Auto-claim run ownership unless `--readonly`.
 - Disk verdict drives `next_recommended_command` (`resolveCompletionStatuses`).
 

package/.agents/skills/harness-sentrux-repair/SKILL.md

@@ -8,7 +8,7 @@ description: |
 
 # harness-sentrux-repair
 
-Structured structural feedback for ultimate-pi harness (ADR 0052). **OSS CLI only.**
+Structured structural feedback for the harness. **OSS CLI only.**
 
 ## Artifacts (per run)
 

package/.agents/skills/harness-sentrux-setup/SKILL.md

@@ -20,7 +20,7 @@ description: Bootstrap Sentrux architectural rules for harness projects — seed
 | **Sync** | `sentrux-rules-sync.mjs`, `/harness-sentrux-sync` | Regenerates `rules.toml` from manifest after intent change |
 | **Observation** | `/harness-run`, `/harness-review` | `harness-sentrux-cli.mjs gate --save` / `check` / `gate` → `artifacts/sentrux-signal.yaml` |
 
-Never auto-sync manifest from directory trees. Material manifest edits need steward evidence + chair approval (ADR 0009).
+Never auto-sync manifest from directory trees. Material manifest edits need steward evidence + chair approval.
 
 ## Canonical layout
 
@@ -63,7 +63,7 @@ Do **not** copy ultimate-pi's layer paths blindly into unrelated layouts — edi
 
 ## References
 
-- ADR 0009 — `.pi/harness/docs/adrs/0009-sentrux-rules-lifecycle.md`
+- Rules lifecycle policy: manifest is source of truth; bootstrap/sync regenerate rules from approved intent.
 - Scripts — `.pi/scripts/sentrux-rules-sync.mjs`, `harness-sentrux-bootstrap.mjs`, `harness-sentrux-cli.mjs`
 - Agents — `harness/sentrux-bootstrap` (setup), `harness/sentrux-steward` (intent proposals)
 - Specs — `sentrux-manifest-proposal.schema.json`, `sentrux-signal.schema.json`

package/.agents/skills/harness-spec/SKILL.md

@@ -17,7 +17,7 @@ description: Draft or refine harness artifact contracts under .pi/harness/specs.
 2. Edit or add schema under `.pi/harness/specs/`.
 3. Update affected extensions to emit matching custom entries.
 4. Run `node "$UP_PKG/.pi/scripts/harness-verify.mjs"` (see `.pi/scripts/README.md`).
-5. Add or update an ADR under `.pi/harness/docs/adrs/` for breaking changes.
+5. Add or update a formal decision record in the target project's standard decision-log location for breaking changes.
 
 ## Rules
 

package/.agents/skills/harness-steer/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: harness-steer
-description: Post-review repair loop via harness-steer and executor repair mode (ADR 0044).
+description: Post-review repair loop via harness-steer and executor repair mode.
 ---
 
 # harness-steer
@@ -11,4 +11,4 @@ Use after `/harness-review` when `artifacts/review-outcome.yaml` has `remediatio
 2. Set policy phase `execute`; spawn `harness/running/executor` with `mode: repair`.
 3. Always follow with `/harness-review`.
 
-See `.pi/prompts/harness-steer.md` and `.pi/harness/docs/adrs/0044-harness-steer-loop.md`.
+See `.pi/prompts/harness-steer.md` for the steer-loop procedure and guardrails.

package/.agents/skills/posthog-analyst/SKILL.md

@@ -264,7 +264,7 @@ status: complete
 | Medium | ... | ... | ... | ... |
 
 ## Next Steps
-[What to do with these findings. Suggest ADR if recommendations are significant.]
+[What to do with these findings. Suggest a formal decision record update if recommendations are significant.]
 ```
 
 After filing, update `vault/wiki/index.md` (add to analyses if category exists, or note inline), update `vault/wiki/log.md` (append entry at TOP), and update `vault/wiki/hot.md` (add key findings to Recent Context).

package/.agents/skills/sentrux/SKILL.md

@@ -42,7 +42,7 @@ Run from the **target repo root** (where `.sentrux/rules.toml` lives), or prefer
 | CI / pre-commit | `node "$UP_PKG/.pi/scripts/harness-sentrux-cli.mjs" check` | Exit 0 = pass, 1 = violations |
 | Before agent work | `node "$UP_PKG/.pi/scripts/harness-sentrux-cli.mjs" gate --save` | Save session baseline |
 | After agent work | `node "$UP_PKG/.pi/scripts/harness-sentrux-cli.mjs" gate` | Detect degradation vs baseline |
-| Harness run/review capture | `harness-sentrux-report.mjs` + `harness-sentrux-diagnostics.mjs` | Single scan → JSON artifacts (ADR 0052) |
+| Harness run/review capture | `harness-sentrux-report.mjs` + `harness-sentrux-diagnostics.mjs` | Single scan → JSON artifacts |
 | Explore structure | `sentrux` or `sentrux .` | GUI treemap (optional) |
 
 Typical agent loop:
@@ -77,7 +77,7 @@ Custom TOML outside `# --- harness:managed:start/end ---` is preserved on sync.
 | `harness-verify.mjs` | Runs rules sync and Sentrux checks when rules are present |
 | **observation-bus** | Maps `harness-sentrux-signal` custom entries → evaluator observations |
 | **harness-sentrux-repair** skill | Report/diagnostics scripts + `sentrux-repair-advisor` + repair plan artifact |
-| **harness-eval** | Evaluate phase may require a Sentrux quality signal per ADR 0006 |
+| **harness-eval** | Evaluate phase may require a Sentrux quality signal before promotion |
 
 High level: **execute** runs one capture (`sentrux-report.json`, `sentrux-diagnostics.json`, signal v1.1.0); **review** may spawn **sentrux-repair-advisor** (Phase 1b); **steer** merges repair plan into `repair-brief.yaml`. No Sentrux Pro or MCP in Pi sessions.
 
@@ -96,6 +96,6 @@ High level: **execute** runs one capture (`sentrux-report.json`, `sentrux-diagno
 
 ## References
 
-- ADR 0006 — `.pi/harness/docs/adrs/0006-sentrux-dual-layer.md`
-- ADR 0009 — `.pi/harness/docs/adrs/0009-sentrux-rules-lifecycle.md`
+- Quality gate policy: require a structural signal for evaluate/promotion decisions when configured.
+- Rules lifecycle policy: manifest is source of truth; sync rules from manifest after approved intent changes.
 - `CONTRIBUTING.md` — Sentrux quick start

package/.agents/skills/web-retrieval/SKILL.md

@@ -160,4 +160,4 @@ Diagnostics: `python3 "$UP_PKG/.pi/scripts/harness-web.py" status` (JSON).
 | `HARNESS_WEB_HEURISTIC_ANGLES_FILE` | — | Extra heuristic angles YAML |
 | `HARNESS_WEB_FAST_MODEL` / `EXPANDER` / `QUALITY` | — | Web subagent models |
 
-See `.pi/harness/docs/harness-web-search.md` for internals.
+Internal implementation notes are package-maintainer-only; this skill already contains the external-facing operating guidance.

package/.pi/agents/harness/ls-lint-steward.md

@@ -7,7 +7,7 @@ max_turns: 16
 
 You are the **Harness ls-lint Steward** — filesystem **naming intent** governance, not setup or execution.
 
-**Practice:** Architecture governance for path hygiene; integrated change control (PMBOK). See `.pi/harness/docs/practice-map.md` phase 4e.
+**Practice:** Architecture governance for path hygiene; integrated change control (PMBOK).
 
 ## Mission
 
@@ -27,7 +27,7 @@ Read `HarnessSpawnContext` (`run_id`, `run_dir`, `plan_packet_path`, `task_summa
 4. Optional: `node "$UP_PKG/.pi/scripts/harness-ls-lint-cli.mjs"` — cite violation messages only; do not rename files.
 5. Classify proposal:
    - `none` — existing rules cover changes
-   - `tune_rule` — adjust a convention for one path glob (e.g. regex for ADRs)
+   - `tune_rule` — adjust a convention for one path glob (e.g. regex for decision-record filenames)
    - `add_scoped_rule` — new directory-specific rules
    - `add_ignore` — exclude generated or third-party trees
    - `change_global` — repo-wide default convention change (material)
@@ -38,7 +38,7 @@ Call **`submit_ls_lint_manifest_proposal`** before exit with document matching `
 
 - `manifest_patch`: JSON Merge Patch against current manifest (minimal diff).
 - `evidence[]`: at least one entry per non-`none` change; prefer `source: graphify` or `ls-lint`.
-- `adr_required: true` and `adr_draft` when material (`change_global`, new top-level convention).
+- When changes are material (`change_global`, new top-level convention), include the schema fields that mark a formal decision record as required and provide draft decision text.
 - `human_required: true` when `change_class` is not `none` and not a narrow `add_ignore` with clear evidence.
 
 ## Guardrails

package/.pi/agents/harness/planning/decompose.md

@@ -7,7 +7,7 @@ max_turns: 12
 
 You are the **Harness problem-framing agent (Phase 2a — lakes / scope)**.
 
-**Inspection role:** Outcome author (lake-sized units, not ticket WBS). See `.pi/harness/docs/practice-map.md` and ADR 0042.
+**Inspection role:** Outcome author (lake-sized units, not ticket WBS).
 
 ## Mission
 

package/.pi/agents/harness/planning/execution-plan-author.md

@@ -22,7 +22,7 @@ Task summary, `PlanDecompositionBrief`, `PlanHypothesisBrief`, draft scope/accep
 5. **Schedule** — `schedule_metadata.critical_path_work_item_ids` for med/high risk tasks.
 6. **wbs_dictionary** — one line per non-trivial work_item (inputs, outputs, owner role).
 7. **risk_register** — ≥3 risks for med/high with mitigation and trigger.
-8. **sprint_contract** — ADR-020 done_criteria types, checkpoints, definition of done.
+8. **sprint_contract** — explicit done_criteria types, checkpoints, and definition of done.
 9. **Quality left** — verify/lint/test work_items in early phases when risk ≥ med.
 10. **done_criteria** — typed per work_item (build | test | verify | docs | deploy as applicable).
 

package/.pi/agents/harness/planning/hypothesis-validator.md

@@ -5,7 +5,7 @@ thinking: medium
 max_turns: 10
 ---
 
-**Inspection role:** Blind verifier (independent verification; debate R1 only). See `.pi/harness/docs/practice-map.md`.
+**Inspection role:** Blind verifier (independent verification; debate R1 only).
 
 ## Your task
 

package/.pi/agents/harness/planning/hypothesis.md

@@ -7,7 +7,7 @@ max_turns: 14
 
 You are the **Harness planning hypothesis generator (Phase 2b — DARWIN)**.
 
-**Role:** Approach author after WBS (Lean hypothesis-driven planning). Requires `artifacts/decomposition.yaml`. See `.pi/harness/docs/practice-map.md`.
+**Role:** Approach author after WBS (Lean hypothesis-driven planning). Requires `artifacts/decomposition.yaml`.
 
 ## Mission
 

package/.pi/agents/harness/planning/plan-adversary.md

@@ -5,7 +5,7 @@ thinking: medium
 max_turns: 14
 ---
 
-**Inspection role:** Red team (adversarial review). See `.pi/harness/docs/practice-map.md`.
+**Inspection role:** Red team (adversarial review).
 
 ## Your task
 

package/.pi/agents/harness/planning/plan-evaluator.md

@@ -5,13 +5,13 @@ thinking: medium
 max_turns: 14
 ---
 
-**Inspection role:** Inspector (neutral Fagan-style checklist). See `.pi/harness/docs/practice-map.md`.
+**Inspection role:** Inspector (neutral Fagan-style checklist).
 
 ## Your task
 
 Score the ExecutionPlan against Validation Checks for one Review Gate round. Emit stable `checks[]` with ids and messenger-ready `claim_ids`. You are not an advocate for the plan.
 
-Parent passes `debate_round_focus`: `spec` | `wbs` | `schedule` | `quality`. Use rubric ids from `.pi/harness/docs/planning-rubrics.md` for that focus.
+Parent passes `debate_round_focus`: `spec` | `wbs` | `schedule` | `quality`. Use focus-specific rubric ids provided in the spawn context for that focus.
 
 ## Process
 

package/.pi/agents/harness/planning/plan-synthesizer.md

@@ -5,7 +5,7 @@ description: Lake-first plan synthesis for low/med risk — problem framing, hyp
 
 # Plan synthesizer
 
-You produce **lake-sized** outcomes (ADR 0042), not ticket-granularity WBS. Read `artifacts/planning-context.yaml`, research briefs, and prior artifacts from disk paths in `HarnessSpawnContext` — do not re-run graphify when coverage is already ok.
+You produce **lake-sized** outcomes, not ticket-granularity WBS. Read `artifacts/planning-context.yaml`, research briefs, and prior artifacts from disk paths in `HarnessSpawnContext` — do not re-run graphify when coverage is already ok.
 
 ## Outputs (all required on disk)
 
@@ -15,7 +15,7 @@ You produce **lake-sized** outcomes (ADR 0042), not ticket-granularity WBS. Read
 
 ## Rules
 
-- Use **`submit_*({ source_path })`** when drafts exist on disk (ADR 0043); otherwise `document`.
+- Use **`submit_*({ source_path })`** when drafts exist on disk; otherwise `document`.
 - Do not spawn subprocesses; you are the subprocess.
 - Match schemas under `.pi/harness/specs/`.
 - Parent runs `validate-plan-dag.mjs` after merge into `plan-packet.yaml`.

package/.pi/agents/harness/planning/review-integrator.md

@@ -5,7 +5,7 @@ thinking: medium
 max_turns: 12
 ---
 
-**Inspection role:** Recorder / integration PM (round synthesis). Parent is chair. See `.pi/harness/docs/practice-map.md`.
+**Inspection role:** Recorder / integration PM (round synthesis). Parent is chair.
 
 ## Your task
 

package/.pi/agents/harness/planning/sprint-contract-auditor.md

@@ -1,22 +1,22 @@
 ---
-description: Plan-phase ADR-020 sprint contract auditor.
+description: Plan-phase sprint contract auditor.
 extensions: false
 thinking: medium
 max_turns: 12
 ---
 
-**Inspection role:** Definition of Done auditor (sprint contract). See `.pi/harness/docs/practice-map.md`.
+**Inspection role:** Definition of Done auditor (sprint contract).
 
 ## Your task
 
-Audit `execution_plan.sprint_contract` and work_item `done_criteria` against ADR-020 (Sprint Contract, Done Criteria Types, Keep Quality Left).
+Audit `execution_plan.sprint_contract` and work_item `done_criteria` against sprint-contract rules (Done Criteria Types, Keep Quality Left).
 
 Required when `debate_round_focus` is `quality` or round_index ≥ 4. Optional spot-check on round 2 if done_criteria are sparse.
 
 ## Process
 
 1. Read `plan-packet.yaml` execution_plan section and sprint_contract block.
-2. Verify done_criteria types cover: build, test, verify, docs (as applicable per ADR-020).
+2. Verify done_criteria types cover: build, test, verify, docs (as applicable).
 3. List checkpoint gaps between phases (missing verify/lint/test work_items when risk ≥ med).
 4. Flag “quality at end only” plans without explicit risk acceptance in risk_register.
 5. Cross-check integrator disputes from same round if transcript provided — do not contradict without note.
@@ -28,7 +28,7 @@ Before ending, call `submit_sprint_audit` exactly once with the full document. P
 
 ## Guardrails
 
-- Cite ADR-020 rule ids in rationale fields.
+- Cite sprint-contract rule ids in rationale fields.
 - Read-only; parent persists artifact.
 
 Bus label: `SprintContractAuditorAgent`.

package/.pi/agents/harness/running/executor.md

@@ -71,7 +71,7 @@ harness-lens may fix indentation on anchored `edit.text` before apply.
 2. **Read** anchored regions you will change.
 3. **Edit** minimally with batched anchored `edit`.
 
-Never use `replace_symbol`, `rename_symbol`, or similar — use `sg` + anchored edit only ([ADR 0045](.pi/harness/docs/adrs/0045-harness-lens-minimal-contract.md)).
+Never use `replace_symbol`, `rename_symbol`, or similar — use `sg` + anchored edit only.
 
 ## Post-edit verification (before handoff)
 

package/.pi/agents/harness/sentrux-repair-advisor.md

@@ -7,7 +7,7 @@ max_turns: 14
 
 You are the **Harness Sentrux Repair Advisor** — turn measured structural debt into a bounded repair plan for steer/executor.
 
-**Practice:** Fitness-function feedback loop (Ford/Richards); generator–evaluator separation. See `.pi/harness/docs/practice-map.md` phase 4e and ADR 0052.
+**Practice:** Fitness-function feedback loop (Ford/Richards); generator–evaluator separation.
 
 ## Mission
 

package/.pi/agents/harness/sentrux-steward.md

@@ -7,7 +7,7 @@ max_turns: 16
 
 You are the **Harness Sentrux Steward** — architectural **intent** governance, not setup or execution.
 
-**Practice:** Architecture governance + fitness functions (Ford/Richards); integrated change control (PMBOK). See `.pi/harness/docs/practice-map.md` phase 4e.
+**Practice:** Architecture governance + fitness functions (Ford/Richards); integrated change control (PMBOK).
 
 ## Mission
 
@@ -38,7 +38,7 @@ Call **`submit_sentrux_manifest_proposal`** before exit with document matching `
 
 - `manifest_patch`: JSON Merge Patch against current manifest (minimal diff).
 - `evidence[]`: at least one entry per non-`none` change; prefer `source: graphify`.
-- `adr_required: true` and `adr_draft` when material (new layer or boundary affecting multiple agents).
+- When changes are material (new layer or boundary affecting multiple agents), include the schema fields that mark a formal decision record as required and provide draft decision text.
 - `human_required: true` when `change_class` is not `none` and not a single numeric `tune_constraint` with clear sentrux evidence.
 
 ## Guardrails

package/.pi/extensions/agt-kill-switch.ts

@@ -12,7 +12,11 @@ import {
 
 const killSwitch = new KillSwitch({ enabled: true });
 
-import { recordHarnessPolicyDeny } from "../lib/agt/kill-switch-state.js";
+import {
+	armHarnessKillSwitch,
+	isHarnessKillSwitchDisarmed,
+	recordHarnessPolicyDeny,
+} from "../lib/agt/kill-switch-state.js";
 
 export function getHarnessKillSwitch(): KillSwitch {
 	return killSwitch;
@@ -34,6 +38,7 @@ export default function agtKillSwitch(pi: ExtensionAPI) {
 		const prompt = userVisiblePromptSlice(event.prompt);
 		if (hasHarnessAbortSignal(prompt)) {
 			const sessionId = ctx.sessionManager.getSessionId();
+			armHarnessKillSwitch(sessionId);
 			await killSwitch.kill(sessionId, {
 				reason: "harness-abort command",
 			});
@@ -43,6 +48,7 @@ export default function agtKillSwitch(pi: ExtensionAPI) {
 
 	pi.on("tool_call", async (_event, ctx) => {
 		const sessionId = ctx.sessionManager.getSessionId();
+		if (isHarnessKillSwitchDisarmed(sessionId)) return undefined;
 		const history = killSwitch.getHistory();
 		const armed = history.some((h) => h.agentId === sessionId);
 		if (armed) {

package/.pi/extensions/harness-plan-approval.ts

@@ -192,11 +192,19 @@ export default function harnessPlanApproval(pi: ExtensionAPI) {
 			if (runCtx?.run_id) {
 				const gate = await validatePlanDebateGate(projectRoot, runCtx.run_id);
 				if (!gate.ok) {
+					const { buildPlanDebateGateRecovery } = await import(
+						"../lib/plan-debate-gate.js"
+					);
+					const recovery = await buildPlanDebateGateRecovery(
+						projectRoot,
+						runCtx.run_id,
+						gate,
+					);
 					return {
 						content: [
 							{
 								type: "text",
-								text: `approve_plan blocked — plan debate gate incomplete:\n- ${gate.errors.join("\n- ")}`,
+								text: `approve_plan blocked — plan debate gate incomplete:\n\n${recovery}`,
 							},
 						],
 						details: {