cc-codeconductor 1.1.0 → 1.2.0

package/presets/claude/settings.json

@@ -151,15 +151,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "if echo \"$CLAUDE_TOOL_INPUT_FILE_PATH\" | grep -qE '\\.(ts|tsx|js|jsx|mjs|cjs|json|jsonc|md|mdx|css|scss|html|astro|yaml|yml)$'; then npx --no-install prettier --write \"$CLAUDE_TOOL_INPUT_FILE_PATH\" 2>/dev/null || true; fi"
-          },
-          {
-            "type": "command",
-            "command": "if echo \"$CLAUDE_TOOL_INPUT_FILE_PATH\" | grep -qE '\\.(ts|tsx|js|jsx|mjs|cjs)$'; then npx --no-install eslint --fix \"$CLAUDE_TOOL_INPUT_FILE_PATH\" 2>/dev/null || true; fi"
-          },
-          {
-            "type": "command",
-            "command": "if echo \"$CLAUDE_TOOL_INPUT_FILE_PATH\" | grep -qE '\\.py$'; then ruff format \"$CLAUDE_TOOL_INPUT_FILE_PATH\" 2>/dev/null && ruff check --fix \"$CLAUDE_TOOL_INPUT_FILE_PATH\" 2>/dev/null || true; fi"
+            "command": "node .claude/hooks/invoke-hook.cjs post-tool"
           }
         ]
       }
@@ -170,7 +162,17 @@
         "hooks": [
           {
             "type": "command",
-            "command": "if echo \"$CLAUDE_TOOL_INPUT_COMMAND\" | grep -qE '(\\.env|secrets/|id_rsa|\\.pem|\\.key)\\b' && echo \"$CLAUDE_TOOL_INPUT_COMMAND\" | grep -qE '(cat|less|more|head|tail|cp |mv |scp )'; then echo 'Bloqueado: intento de leer archivos sensibles' >&2; exit 2; elif echo \"$CLAUDE_TOOL_INPUT_COMMAND\" | grep -qE '^\\s*git\\s+(push|reset\\s+--hard)' || echo \"$CLAUDE_TOOL_INPUT_COMMAND\" | grep -qE '^\\s*git\\s+clean\\s+(-[a-z]*f[a-z]*|--force)' || echo \"$CLAUDE_TOOL_INPUT_COMMAND\" | grep -qE '^\\s*git\\s+branch\\s+(-D|--delete\\s+--force)' || echo \"$CLAUDE_TOOL_INPUT_COMMAND\" | grep -qE '^\\s*git\\s+checkout\\s+(-f|--force|--discard-changes|--theirs|--ours|-\\s|-$)' || echo \"$CLAUDE_TOOL_INPUT_COMMAND\" | grep -qE '^\\s*git\\s+restore\\s+(-f|--force|--discard-changes|--theirs|--ours)'; then echo \"Bloqueado: El agente no tiene autoridad sobre este comando.\" >&2; exit 2; fi"
+            "command": "node .claude/hooks/invoke-hook.cjs pre-tool"
+          }
+        ]
+      }
+    ],
+    "SessionStart": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node .claude/hooks/invoke-hook.cjs session-start"
           }
         ]
       }
@@ -180,7 +182,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "echo \"[subagent fin] $(date -Iseconds)\" >> ~/.claude/subagent.log"
+            "command": "node -e \"var fs=require('fs');var os=require('os');var p=require('path');var dir=p.join(os.homedir(),'.claude');fs.mkdirSync(dir,{recursive:true});fs.appendFileSync(p.join(dir,'subagent.log'),'[subagent fin] '+new Date().toISOString()+'\\n');\""
           }
         ]
       }

package/presets/claude/skills/backlog/SKILL.md

@@ -1,91 +1,61 @@
 ---
 name: backlog
 description: >
-  Author BACKLOG.md and OpenSpec change folders for CodeConductor.
-  Trigger: /cc-backlog, /cc:backlog, creating or appending backlog items,
-  writing BACKLOG.md, or preparing work for /cc-openspec.
+  Guides agents through authoring BACKLOG.md and OpenSpec change folders.
+  Use when running /cc-backlog or /cc:backlog, creating or appending backlog
+  items, or preparing work for /cc-openspec. Delivery is skill openspec.
 ---
 
 # Backlog authoring
 
-Use this skill to **create or append** `BACKLOG.md` and generate OpenSpec
-change docs. Delivery of an existing item is `/cc-openspec` (skill `openspec`).
+## Overview
 
-## BACKLOG.md contract
+Create or append `BACKLOG.md`, then `openspec validate` / `plan`. Do not deliver
+the item here.
 
-Canonical template: `presets/templates/BACKLOG.md` (or the installed copy).
-Required sections:
+## When to Use
 
-- `## Global` — Product, Strategy, Policy, Review required, TDD required
-- `## Items` — active entries
-- `## Archive` — completed entries (never re-execute; never rewrite)
+- `/cc-backlog`, first backlog in a repo, or appending `### BC-xxx` items
 
-Each item: `### BC-001 | Short title` with Priority (P0–P3), Status, Type,
-Depends on, Description, Scope, Out of scope, Acceptance (measurable checklist).
+**NOT** for executing an item (`openspec`) or for scorecards (`evaluation`).
 
-Status after grilling: `READY`. `openspec plan` then moves the item to `PLANNED`.
+## Process
 
-## Create vs append
+1. If `graphify-out/graph.json` exists, `graphify query "<objectives>"`. Then
+   `repo-explorer`. Scope names real files.
+2. Invoke `task-coach`. One grilling question per assumption. Reject vague
+   acceptance ("improve UX"). At most 3 `[NEEDS CLARIFICATION]`.
+3. `ccep evaluate --command backlog`. If `stop`, wait for the human.
+4. Create `BACKLOG.md` from `presets/templates/BACKLOG.md` or append under
+   `## Items`. Do not rewrite `## Global` or `## Archive`.
+5. Next ID = max numeric suffix in Items + Archive + 1, zero-padded (`BC-013`).
+6. `bun run dev openspec validate` (or `npx cc-codeconductor`). Fix until valid.
+7. `openspec plan BC-xxx` for each **new** item this run. Then tell the user
+   to run `/cc-openspec`.
 
-- **No `BACKLOG.md`:** create it from the template. Set Global `Product` from
-  `package.json` `name` when present.
-- **File exists:** append new `### BC-xxx` blocks under `## Items`. Do not
-  rewrite `## Global` or `## Archive`.
+Required sections: `## Global`, `## Items`, `## Archive`. Each item:
+`### BC-001 | Title` with Priority, Status (`READY` after grilling), Type,
+Depends on, Description, Scope, Out of scope, Acceptance.
 
-Next ID = max numeric suffix across Items and Archive, plus one, zero-padded
-to three digits (`BC-013` after `BC-012`).
+Local artifacts (`BACKLOG.md`, `openspec/`, `.codeconductor/openspec-state.json`)
+are gitignored in consumer projects. Do not `git add` them.
 
-## Wayfinding (before Scope)
+## Common Rationalizations
 
-If `graphify-out/graph.json` exists, run `graphify query "<objectives>"` (and
-`graphify path` / `graphify explain` when needed). Then invoke `repo-explorer`.
-Scope must name real files or modules. Do not write `BACKLOG.md` in this step.
+| Rationalization | Reality |
+| --- | --- |
+| This fix is small; skip the Task Card | Every item needs measurable acceptance. |
+| I'll validate later | Do not plan until `openspec validate` passes. |
+| Archive can be rewritten | Archive is history. Never rewrite or re-execute. |
 
-## Grilling (before write)
+## Red Flags
 
-Invoke `task-coach`. One grilling question per assumption. Reject vague
-acceptance ("improve UX", "fix bugs"). Criteria must be measurable (same rules
-as `openspec validate` / `VAGUE_ACCEPTANCE`).
+- Acceptance that cannot fail a check
+- Editing `openspec-state.json` by hand
+- Planning an invalid backlog
 
-Unresolved questions go in `questionsForUser`. Run `ccep evaluate --command
-backlog`. If `stop` is true, **STOP** and wait for the human.
+## Verification
 
-Do not write items until the gate passes.
-
-## Validate loop
-
-After writing:
-
-```bash
-npx cc-codeconductor openspec validate
-```
-
-Local CodeConductor dogfood: `bun run dev openspec validate`.
-
-If invalid: list errors and recommendations, show the canonical structure,
-fix the file, re-validate. Do not plan until valid.
-
-## Plan new items only
-
-For each **new** `BC-xxx` this run:
-
-```bash
-npx cc-codeconductor openspec plan BC-xxx
-```
-
-That writes `openspec/changes/<slug>/` (`proposal.md`, `design.md`, `tasks.md`,
-`specs/`). Then tell the user to run `/cc-openspec` (optionally with the ID).
-
-## Local artifacts — do not version
-
-In consumer projects these paths are gitignored (see `init`):
-
-- `BACKLOG.md`
-- `openspec/`
-- `.codeconductor/openspec-state.json`
-
-Do **not** `git add` them. Do not edit `openspec-state.json` by hand.
-
-## Delivery
-
-Format and state machine: skill `openspec`. Authoring is this skill.
+- [ ] `openspec validate` exit 0
+- [ ] New items have `FR`/`SC`-ready measurable acceptance
+- [ ] User pointed at `/cc-openspec` for delivery

package/presets/claude/skills/evaluation/SKILL.md

@@ -1,42 +1,65 @@
 ---
 name: evaluation
 description:
-  Agent scorecard criteria, outcome tracking, model profiles, and evaluation CLI.
-  Use when running /cc:scorecard or measuring deliverable quality.
+  Guides agents through scorecards, outcomes, model profiles, and eval suites.
+  Use when running /cc-scorecard or /cc:scorecard, measuring a deliverable, or
+  checking workflow gates with suite-run.
 ---
 
-# Evaluation Skill
+# Evaluation
 
-## Scorecard criteria (8 weighted)
+## Overview
 
-See `docs/agent-scorecard.md`. Pass threshold: weighted score >= 2.0, no criterion at 0.
+A scorecard measures the deliverable against eight weighted criteria. Spec
+quality checklists are reviewer-owned. "Seems right" is not a verdict.
 
-## CLI
+Pass threshold: weighted score >= 2.0 and no criterion at 0.
 
-```bash
-npx cc-codeconductor scorecard create --task BC-001 --from-diff
-npx cc-codeconductor scorecard record --task BC-001 --verdict PASS --score 2.5
-npx cc-codeconductor scorecard list
-npx cc-codeconductor scorecard aggregate
-npx cc-codeconductor scorecard models
-npx cc-codeconductor scorecard regression
-npx cc-codeconductor scorecard matrix
-npx cc-codeconductor scorecard compare-models
-npx cc-codeconductor scorecard prompt-diff 0.4.0 0.5.0 --agent architect
+## When to Use
+
+- After implement/review, before `openspec archive`
+- Comparing models or prompt versions
+- Proving the workflow tools still work (`suite-run`)
+
+**NOT** for rewriting specs (reviewer checklist) or for implementing code.
+
+## Process
+
+Local: `bun run dev`. Published: `npx cc-codeconductor`.
+
+```text
+scorecard create --task BC-001 --from-diff
+scorecard record --task BC-001 --verdict PASS --score 2.5
+scorecard list | aggregate | models | regression | matrix | compare-models
+scorecard prompt-diff 0.4.0 0.5.0 --agent architect
+scorecard experiment start --suite harness-v1
+scorecard suite-run --suite workflow-gates
+scorecard suite-run --suite hook-guardrails
+scorecard suite-run --suite scorecard-signals
 ```
 
-## Outcome tracking
+`openspec analyze` can auto-suggest `acceptance` / `tests` on `--from-diff`.
+Archive needs PASS when review is required.
 
-Append-only: `.codeconductor/evaluation/outcomes.jsonl`
+Outcomes append to `.codeconductor/evaluation/outcomes.jsonl`.
 
-Record after each phase (openspec) and after review gate with agent, model, verdict, optional cost/tokens.
+## Common Rationalizations
 
-## Execution profiles
+| Rationalization | Reality |
+| --- | --- |
+| I'll fill the scorecard by hand without a diff | Use `--from-diff` and runner evidence. |
+| Suites are optional toys | `suite-run` is the workflow tool that proves gates. |
+| Handmade TDD JSON is fine | The runner rejects it. |
 
-`.codeconductor/evaluation/execution-profile.yml` — `balanced`, `quality`, `economical`.
+## Red Flags
 
-Use `scorecard models` before OpenSpec execute loop to show phase → agent → model.
+- PASS with a criterion at 0
+- Archive without a recorded scorecard when review is required
+- Declaring the workflow ready without `suite-run` or `scorecard record`
 
-## Verdicts
+## Verification
 
-PASS / REVISE / REJECT — see scorecard calculator rules in docs.
+- [ ] Scorecard created from diff (or explicit scores)
+- [ ] Verdict PASS / REVISE / REJECT recorded
+- [ ] For process changes: `scorecard suite-run --suite hook-guardrails` (and
+      `workflow-gates` / `scorecard-signals` when those gates changed)

package/presets/claude/skills/openspec/SKILL.md

@@ -1,58 +1,66 @@
 ---
 name: openspec
 description:
-  OpenSpec backlog format, state machine, and delivery workflow for CodeConductor.
-  Use when running /cc:openspec or delivering a BACKLOG.md item.
-  To create or append BACKLOG.md, use /cc:backlog (skill backlog).
+  Guides agents through OpenSpec delivery from BACKLOG.md (validate, analyze,
+  test-before-implement, scorecard, archive). Use when running /cc-openspec,
+  /cc:openspec, or delivering an existing backlog item. Authoring BACKLOG.md
+  is skill backlog, not this skill.
 ---
 
-# OpenSpec / BACKLOG Skill
+# OpenSpec delivery
 
-Authoring (create or append `BACKLOG.md`, then `openspec validate` / `plan`) is
-`/cc:backlog` and skill `backlog`. This skill is **delivery**.
+## Overview
 
-## BACKLOG.md contract
+This skill delivers an existing `BACKLOG.md` item. It is a workflow with CLI
+gates, not a reference doc. Specs describe WHAT; `design.md` describes HOW.
 
-`BACKLOG.md` at repo root is the operational queue. Required sections:
+## When to Use
 
-- `## Global` — Product, Strategy, Policy, Review required, TDD required
-- `## Items` — active backlog entries
-- `## Archive` — completed entries (do not re-execute)
+- `/cc-openspec` or `openspec next` / `plan` / `done` / `archive`
+- An item is `READY` or later and must move through the state machine
 
-Each item: `### BC-001 | Short title` with Priority (P0–P3), Status, Type, Depends on, Description, Scope, Out of scope, Acceptance (measurable checklist).
+**NOT** for creating `BACKLOG.md` (use skill `backlog`) or for stack-specific
+coding rules.
 
-## Status machine
+## Process
 
-`TODO` → `READY` → `PLANNED` → `IN_PROGRESS` → `REVIEW` → `DONE` → Archive
+Local CLI is `bun run dev`. Published package is `npx cc-codeconductor`.
 
-`BLOCKED` can return to `READY` when resolved. Reviewer rejection: `REVIEW` → `IN_PROGRESS`.
+1. `openspec validate` — must pass before delivery.
+2. `openspec plan BC-xxx` if the item is not yet `PLANNED`.
+3. `openspec analyze --output json` — CRITICAL findings exit 1. Do not implement.
+4. Phases: discover (`repo-explorer`) → design (`architect`) → test (`tester`) →
+   implement (`implementer`) → review (`reviewer`). If Global `TDD required: yes`,
+   test runs before implement.
+5. `openspec done` on test/implement requires `captureTddSuiteEvidence`. Handmade
+   evidence JSON is rejected.
+6. `scorecard create --task BC-xxx --from-diff` then record a verdict.
+7. `openspec archive` only after human review when `Review required: yes` and
+   the scorecard is PASS.
 
-## CLI commands
+Status machine: `TODO` → `READY` → `PLANNED` → `IN_PROGRESS` → `REVIEW` → `DONE`
+→ Archive. `BLOCKED` returns to `READY`. Reviewer rejection: `REVIEW` →
+`IN_PROGRESS`.
 
-```bash
-npx cc-codeconductor openspec validate   # gate — must pass before delivery
-npx cc-codeconductor openspec scan
-npx cc-codeconductor openspec plan BC-001
-npx cc-codeconductor openspec status
-npx cc-codeconductor openspec next
-```
+## Common Rationalizations
 
-## OpenSpec folders
+| Rationalization | Reality |
+| --- | --- |
+| Validate is bureaucracy | `openspec validate` is the gate. Skipping it is a defect. |
+| I'll add tests after green | Global TDD required means tester before implementer. |
+| I'll write the evidence JSON myself | Handmade TDD JSON is rejected. Use the verification runner. |
+| The item is small; skip analyze | `openspec analyze` CRITICAL still stops implement. |
 
-Each item generates `openspec/changes/<slug>/` with `proposal.md`, `design.md`, `tasks.md`, `specs/` — compatible with Fission-AI OpenSpec layout (no external CLI required).
+## Red Flags
 
-## Agent phases
+- Implementing while analyze reports CRITICAL
+- Archive without a PASS scorecard when review is required
+- Acceptance like "improve UX" with no measurable check
 
-| Phase | Agent |
-|-------|-------|
-| discover | repo-explorer |
-| design | architect |
-| test | tester |
-| implement | implementer |
-| review | reviewer |
+## Verification
 
-When Global `TDD required: yes`, test runs before implement.
-
-## Reject vague backlog
-
-Do not process items with acceptance like "improve UX" or "fix bugs". Require verifiable criteria.
+- [ ] `openspec validate` exit 0
+- [ ] `openspec analyze --output json` has no CRITICAL
+- [ ] TDD evidence from the runner when TDD is required
+- [ ] `scorecard create --from-diff` recorded
+- [ ] Suite check (optional): `bun run dev scorecard suite-run --suite workflow-gates`

package/presets/claude/skills/testing-tdd/SKILL.md

@@ -0,0 +1,53 @@
+---
+name: testing-tdd
+description:
+  Guides agents through Red-Green-Refactor with runner-captured evidence.
+  Use when running /cc-tdd-cycle, writing tests before implementation, or
+  Global TDD required is yes.
+---
+
+# Test-Driven Development
+
+## Overview
+
+Red (failing test) → Green (minimal code) → Refactor. Evidence comes from
+`captureTddSuiteEvidence`, not handmade JSON.
+
+## When to Use
+
+- `/cc-tdd-cycle`, new behavior, bug fixes, TDD-required OpenSpec items
+
+**NOT** for docs-only changes or when the Task Card forbids tests.
+
+## Process
+
+1. Write the failing test that encodes one acceptance criterion. Run the suite.
+   It MUST fail (`suiteFails === true`).
+2. Implement the minimum that turns it green. Do not expand scope.
+3. Refactor only with a green suite.
+4. Capture evidence via the verification runner (`openspec done` on test/implement
+   when TDD is required).
+5. Cover happy path, edge, and error for each behavior.
+
+Local: `bun run dev`. Pyramid default: many unit, fewer integration, rare E2E.
+
+## Common Rationalizations
+
+| Rationalization | Reality |
+| --- | --- |
+| I'll add tests later | Later means never. Red first. |
+| This is too small to test | If it can break, it needs a failing test first. |
+| I'll write the evidence JSON | Handmade TDD JSON is rejected. |
+
+## Red Flags
+
+- Tests that assert implementation details instead of behavior
+- Green without a recorded red
+- Skipping error cases
+
+## Verification
+
+- [ ] Suite failed before implement
+- [ ] Suite passed after implement
+- [ ] Runner evidence exists (not handmade)
+- [ ] Optional: `bun run dev scorecard suite-run --suite workflow-gates`

package/presets/claude/skills/using-cc-skills/SKILL.md

@@ -0,0 +1,48 @@
+---
+name: using-cc-skills
+description:
+  Maps incoming work to the CodeConductor slash command and workflow skill.
+  Use when starting a session or deciding which /cc-* command applies.
+---
+
+# Using CodeConductor skills
+
+## Overview
+
+Pick one slash command. Follow its skill. Invoke CLI for gates. Do not invent
+a parallel process.
+
+## When to Use
+
+- Start of a session, ambiguous request, or "which /cc should I run?"
+
+## Process
+
+| Intent | Command | Skill |
+| --- | --- | --- |
+| New backlog item | `/cc-backlog` | `backlog` |
+| Deliver a BC-xxx item | `/cc-openspec` | `openspec` |
+| New feature | `/cc-feature` | `openspec` + `testing-tdd` |
+| Bug fix | `/cc-fix` | `testing-tdd` |
+| Review a diff | `/cc-review` | `evaluation` |
+| TDD cycle only | `/cc-tdd-cycle` | `testing-tdd` |
+| Scorecard / suites | `/cc-scorecard` | `evaluation` |
+
+Then run the matching CLI (`openspec validate`, `scorecard create --from-diff`,
+`hook pre-tool`, `scorecard suite-run`).
+
+## Common Rationalizations
+
+| Rationalization | Reality |
+| --- | --- |
+| I'll skip the slash and just code | Skipping the workflow is a defect. |
+
+## Red Flags
+
+- Two slash commands in parallel that mutate the same files
+- Implementing before `openspec analyze` when a change folder is active
+
+## Verification
+
+- [ ] One command selected and shown to the user
+- [ ] Matching skill loaded before edits

package/presets/codex/AGENTS.md

@@ -64,20 +64,24 @@ Skipping any step is not an optimization. It is a defect.
 
 ## Trigger Phrases
 
-Codex does not load custom slash commands from this preset. Use these natural
-language patterns to activate each workflow:
+Invoke workflows as Codex skills (`$cc-feature`, `$cc-openspec`, …). Custom
+prompts under `~/.codex/prompts` are deprecated. Natural-language phrases still
+work:
 
-| Workflow     | Trigger phrase                                     |
+| Workflow     | Skill / trigger                                    |
 | ------------ | -------------------------------------------------- |
-| Full feature | "Run the feature workflow for: [description]"      |
-| Bug fix      | "Run the fix workflow for: [description]"          |
-| Refactor     | "Run the refactor workflow for: [scope]"           |
-| API contract | "Run the API contract workflow for: [change]"      |
-| DB migration | "Run the database migration workflow for: [scope]" |
-| Code review  | "Run a structured review of: [target]"             |
-| Test plan    | "Create a test plan for: [scope]"                  |
-| Task intake  | "Help me define a Task Card for: [vague request]"  |
-| PageSpeed    | "Run a PageSpeed audit for: [url]"                 |
+| Full feature | `$cc-feature` or "Run the feature workflow for:"   |
+| Bug fix      | `$cc-fix`                                          |
+| Refactor     | `$cc-refactor`                                     |
+| API contract | `$cc-api-contract`                                 |
+| DB migration | `$cc-db-migration`                                 |
+| Code review  | `$cc-review`                                       |
+| Test plan    | `$cc-test-plan`                                    |
+| TDD cycle    | `$cc-tdd-cycle`                                    |
+| Backlog      | `$cc-backlog`                                      |
+| OpenSpec     | `$cc-openspec`                                     |
+| Scorecard    | `$cc-scorecard`                                    |
+| PageSpeed    | `$cc-pagespeed` or "PageSpeed audit"               |
 
 ---
 

package/presets/codex/skills/backlog/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: backlog
+description: >
+  Guides agents through authoring BACKLOG.md and OpenSpec change folders.
+  Use when running /cc-backlog or /cc:backlog, creating or appending backlog
+  items, or preparing work for /cc-openspec. Delivery is skill openspec.
+---
+
+# Backlog authoring
+
+## Overview
+
+Create or append `BACKLOG.md`, then `openspec validate` / `plan`. Do not deliver
+the item here.
+
+## When to Use
+
+- `/cc-backlog`, first backlog in a repo, or appending `### BC-xxx` items
+
+**NOT** for executing an item (`openspec`) or for scorecards (`evaluation`).
+
+## Process
+
+1. If `graphify-out/graph.json` exists, `graphify query "<objectives>"`. Then
+   `repo-explorer`. Scope names real files.
+2. Invoke `task-coach`. One grilling question per assumption. Reject vague
+   acceptance ("improve UX"). At most 3 `[NEEDS CLARIFICATION]`.
+3. `ccep evaluate --command backlog`. If `stop`, wait for the human.
+4. Create `BACKLOG.md` from `presets/templates/BACKLOG.md` or append under
+   `## Items`. Do not rewrite `## Global` or `## Archive`.
+5. Next ID = max numeric suffix in Items + Archive + 1, zero-padded (`BC-013`).
+6. `bun run dev openspec validate` (or `npx cc-codeconductor`). Fix until valid.
+7. `openspec plan BC-xxx` for each **new** item this run. Then tell the user
+   to run `/cc-openspec`.
+
+Required sections: `## Global`, `## Items`, `## Archive`. Each item:
+`### BC-001 | Title` with Priority, Status (`READY` after grilling), Type,
+Depends on, Description, Scope, Out of scope, Acceptance.
+
+Local artifacts (`BACKLOG.md`, `openspec/`, `.codeconductor/openspec-state.json`)
+are gitignored in consumer projects. Do not `git add` them.
+
+## Common Rationalizations
+
+| Rationalization | Reality |
+| --- | --- |
+| This fix is small; skip the Task Card | Every item needs measurable acceptance. |
+| I'll validate later | Do not plan until `openspec validate` passes. |
+| Archive can be rewritten | Archive is history. Never rewrite or re-execute. |
+
+## Red Flags
+
+- Acceptance that cannot fail a check
+- Editing `openspec-state.json` by hand
+- Planning an invalid backlog
+
+## Verification
+
+- [ ] `openspec validate` exit 0
+- [ ] New items have `FR`/`SC`-ready measurable acceptance
+- [ ] User pointed at `/cc-openspec` for delivery