cc-codeconductor 0.4.3 → 0.5.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cc-codeconductor",
-  "version": "0.4.3",
+  "version": "0.5.0",
   "description": "A multi-agent orchestration framework for AI-assisted software engineering workflows.",
   "keywords": [
     "ai",

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

@@ -0,0 +1,6 @@
+---
+name: evaluation
+description: Scorecard and outcome tracking for CodeConductor workflows.
+---
+
+Record outcomes via `scorecard record`. Use `scorecard models` before OpenSpec phases.

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

@@ -0,0 +1,32 @@
+---
+name: openspec
+description:
+  OpenSpec backlog format, state machine, and delivery workflow for CodeConductor.
+  Use when running /cc-openspec or editing BACKLOG.md.
+---
+
+# OpenSpec / BACKLOG Skill
+
+## BACKLOG.md contract
+
+`BACKLOG.md` at repo root is the operational queue. Required sections:
+
+- `## Global` — Product, Strategy, Policy, Review required, TDD required
+- `## Items` — active backlog entries
+- `## Archive` — completed entries (do not re-execute)
+
+Each item: `### BC-001 | Short title` with Priority (P0–P3), Status, Type, Depends on, Description, Scope, Out of scope, Acceptance (measurable checklist).
+
+## Status machine
+
+`TODO` → `READY` → `PLANNED` → `IN_PROGRESS` → `REVIEW` → `DONE` → Archive
+
+## CLI
+
+`openspec validate | scan | plan | status | next`
+
+## Agent phases
+
+discover → repo-explorer, design → architect, test → tester, implement → implementer, review → reviewer.
+
+TDD required: test before implement.

package/presets/agy/workflows/cc-openspec.md

@@ -0,0 +1,62 @@
+---
+name: cc-openspec
+description:
+  Run OpenSpec backlog delivery — validate BACKLOG.md, plan TaskCards, orchestrate
+  agents by phase, review gate, and update backlog state.
+---
+
+# OpenSpec Backlog Workflow
+
+Scope: $ARGUMENTS
+
+---
+
+## Step 0 — Validate (mandatory gate)
+
+Run `npx cc-codeconductor openspec validate`. If invalid, show errors and recommendations, then **STOP**.
+
+---
+
+## Step 1 — Scan
+
+Run `npx cc-codeconductor openspec scan`. Report new, modified, and closed items.
+
+---
+
+## Step 2 — Select item
+
+Use `$ARGUMENTS` BC-id or `npx cc-codeconductor openspec status` for next READY item. **STOP** if none.
+
+---
+
+## Step 3 — Plan
+
+Run `npx cc-codeconductor openspec plan <BC-id>`. Show TaskCards and `openspec/changes/` path.
+
+---
+
+## Step 4 — Execute loop
+
+For each pending card: `npx cc-codeconductor openspec next`, then invoke the listed agent:
+
+- discover → `repo-explorer`
+- design → `architect`
+- test → `tester`
+- implement → `implementer`
+- review → `reviewer`
+
+Use isolated context. Implementer uses a git worktree.
+
+---
+
+## Step 5 — Review gate
+
+Reviewer approves or rejects against acceptance criteria. Reject → `IN_PROGRESS`, **STOP**.
+
+---
+
+## Step 6 — Update
+
+Mark DONE, move to Archive in BACKLOG.md, run `openspec scan`.
+
+Apply skill `openspec` for format and state rules.

package/presets/agy/workflows/cc-scorecard.md

@@ -0,0 +1,17 @@
+---
+name: cc-scorecard
+description:
+  Evaluate deliverable quality — scorecard, outcome tracking, regression checklist.
+---
+
+# Scorecard Evaluation Workflow
+
+Scope: $ARGUMENTS
+
+1. `npx cc-codeconductor scorecard create --task <id> --from-diff`
+2. Complete criteria per docs/agent-scorecard.md
+3. `scorecard regression` if needed
+4. `scorecard record` with verdict and optional cost/tokens
+5. `scorecard aggregate`
+
+Apply skill `evaluation`.

package/presets/claude/commands/cc/openspec.md

@@ -0,0 +1,144 @@
+---
+description: >-
+  [cc: alias] Run OpenSpec backlog delivery — validate BACKLOG.md, plan TaskCards,
+  orchestrate agents by phase, review gate, and update backlog state.
+---
+
+# OpenSpec Backlog Workflow
+
+Scope: $ARGUMENTS
+
+Orchestrate FIFO delivery from `BACKLOG.md`. CodeConductor owns planning; agents execute one TaskCard per phase with the installed preset model for each role.
+
+---
+
+## Step 0 — Validate (mandatory gate)
+
+Run:
+
+```bash
+npx cc-codeconductor openspec validate
+```
+
+If validation fails:
+
+1. List all errors and recommendations from the CLI output.
+2. Show the canonical BACKLOG.md structure (## Global, ## Items, ### BC-001 | Title, Priority, Status, Type, Depends on, Description, Scope, Acceptance).
+3. **STOP.** Do not scan, plan, or execute until the user fixes BACKLOG.md.
+
+---
+
+## Step 1 — Scan
+
+Run:
+
+```bash
+npx cc-codeconductor openspec scan
+```
+
+Report: new items, modified items, closed/archived items, and whether the file changed.
+
+---
+
+## Step 2 — Select item
+
+If `$ARGUMENTS` contains a `BC-xxx` ID, use that item. Otherwise run:
+
+```bash
+npx cc-codeconductor openspec status
+```
+
+Pick the next `READY` item with satisfied dependencies (FIFO by priority). Skip items in `DONE` or `Archive`.
+
+**STOP if no eligible item.** Report backlog status and wait for the user.
+
+---
+
+## Step 3 — Plan
+
+Run:
+
+```bash
+npx cc-codeconductor openspec plan <BC-id>
+```
+
+Show:
+
+- Generated TaskCards (discover → design → test → implement → review when TDD required)
+- Path to `openspec/changes/<slug>/` (proposal, design, tasks, specs)
+
+Update BACKLOG item status to `PLANNED` (CLI does this automatically).
+
+---
+
+## Step 4 — Model matrix and execute loop
+
+Before executing phases, show resolved models:
+
+```bash
+npx cc-codeconductor scorecard models
+```
+
+For each pending TaskCard, run:
+
+```bash
+npx cc-codeconductor openspec next
+```
+
+Invoke the agent named on the card with **isolated** context (`/clear` between phases unless continuation is required):
+
+| Phase | Agent | Role |
+|-------|-------|------|
+| discover | repo-explorer | Map repo and impact |
+| design | architect | Technical plan |
+| test | tester | TDD tests (before implement if TDD required) |
+| implement | implementer | Minimal diff in worktree |
+| review | reviewer | Acceptance + scope gate |
+
+Use the model configured in the installed preset for each agent role.
+
+After each phase:
+
+- Mark progress in deliverable summary.
+- Set TaskCard status to `done` in `.codeconductor/openspec-state.json` when phase completes.
+
+Implementer: create a Git worktree before editing (`git worktree add ../<branch>-session <branch>`).
+
+---
+
+## Step 5 — Review gate
+
+Run regression when BACKLOG Global `Review required: yes`:
+
+```bash
+npx cc-codeconductor scorecard regression
+```
+
+The `reviewer` agent must verify:
+
+- All acceptance criteria from BACKLOG.md
+- Tests pass
+- Scope matches the backlog item
+- No architectural violations
+
+If **rejected**: set item status `IN_PROGRESS`, record findings in state, **STOP** and report to user.
+
+If **approved**: proceed to Step 6.
+
+---
+
+## Step 6 — Scorecard and update backlog
+
+1. `npx cc-codeconductor scorecard create --task <BC-id> --from-diff`
+2. Complete criteria; `scorecard record` with verdict and optional cost/tokens
+3. Set item `Progress: 100%`, `Status: DONE` if PASS
+4. Move item to `## Archive` in BACKLOG.md if DONE
+5. Run `npx cc-codeconductor openspec scan`
+
+Report completion: Task Cards executed, scorecard verdict, change folder path, files changed.
+
+---
+
+## Skill
+
+Apply `.claude/skills/openspec/SKILL.md` for backlog format rules and state transitions.

package/presets/claude/commands/cc/review.md

@@ -122,5 +122,16 @@ If no CRITICAL findings exist:
 
 ## Completion
 
-Deliver the complete Review Report. Never summarize or omit findings. Every
-finding must include a location and an actionable description.
+Deliver the complete Review Report. Never summarize or omit findings.
+
+---
+
+## Step 5 — Scorecard and outcome
+
+```bash
+npx cc-codeconductor scorecard create --from-diff --agent reviewer
+npx cc-codeconductor scorecard record --verdict PASS|REVISE|REJECT --score <weighted>
+npx cc-codeconductor scorecard regression
+```
+
+Map merge recommendation to scorecard verdict. Record outcome for trend tracking.

package/presets/claude/commands/cc/scorecard.md

@@ -0,0 +1,65 @@
+---
+description: >-
+  [cc: alias] Evaluate deliverable quality — scorecard, outcome tracking, regression
+  checklist, and aggregate stats.
+---
+
+# Scorecard Evaluation Workflow
+
+Scope: $ARGUMENTS
+
+---
+
+## Step 1 — Identify task
+
+Use `$ARGUMENTS` as task id (e.g. `BC-001`) or read active item from `npx cc-codeconductor openspec status`.
+
+---
+
+## Step 2 — Create scorecard with auto-signals
+
+```bash
+npx cc-codeconductor scorecard create --task <id> --agent reviewer --from-diff
+```
+
+Review auto-suggested criteria (minimal diff, cc-gain). Complete remaining scores 0–3 per [`docs/agent-scorecard.md`](docs/agent-scorecard.md).
+
+---
+
+## Step 3 — Regression (optional)
+
+```bash
+npx cc-codeconductor scorecard regression
+```
+
+If required checks fail, **STOP** and report failures.
+
+---
+
+## Step 4 — Record outcome
+
+```bash
+npx cc-codeconductor scorecard record --task <id> --agent reviewer --model <model> --verdict PASS --score 2.5
+```
+
+Include `--cost` and `--tokens` when available from session metrics.
+
+---
+
+## Step 5 — Aggregate
+
+```bash
+npx cc-codeconductor scorecard aggregate
+```
+
+Report pass rate and average weighted score.
+
+---
+
+## Routing on verdict
+
+- **PASS** — accept deliverable; update backlog if applicable
+- **REVISE** — return to implementer/tester with findings
+- **REJECT** — route to task-coach for re-scoping
+
+Apply skill `evaluation`.

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

@@ -0,0 +1,42 @@
+---
+name: evaluation
+description:
+  Agent scorecard criteria, outcome tracking, model profiles, and evaluation CLI.
+  Use when running /cc:scorecard or measuring deliverable quality.
+---
+
+# Evaluation Skill
+
+## Scorecard criteria (8 weighted)
+
+See `docs/agent-scorecard.md`. Pass threshold: weighted score >= 2.0, no criterion at 0.
+
+## CLI
+
+```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
+```
+
+## Outcome tracking
+
+Append-only: `.codeconductor/evaluation/outcomes.jsonl`
+
+Record after each phase (openspec) and after review gate with agent, model, verdict, optional cost/tokens.
+
+## Execution profiles
+
+`.codeconductor/evaluation/execution-profile.yml` — `balanced`, `quality`, `economical`.
+
+Use `scorecard models` before OpenSpec execute loop to show phase → agent → model.
+
+## Verdicts
+
+PASS / REVISE / REJECT — see scorecard calculator rules in docs.

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

@@ -0,0 +1,54 @@
+---
+name: openspec
+description:
+  OpenSpec backlog format, state machine, and delivery workflow for CodeConductor.
+  Use when running /cc:openspec or editing BACKLOG.md.
+---
+
+# OpenSpec / BACKLOG Skill
+
+## BACKLOG.md contract
+
+`BACKLOG.md` at repo root is the operational queue. Required sections:
+
+- `## Global` — Product, Strategy, Policy, Review required, TDD required
+- `## Items` — active backlog entries
+- `## Archive` — completed entries (do not re-execute)
+
+Each item: `### BC-001 | Short title` with Priority (P0–P3), Status, Type, Depends on, Description, Scope, Out of scope, Acceptance (measurable checklist).
+
+## Status machine
+
+`TODO` → `READY` → `PLANNED` → `IN_PROGRESS` → `REVIEW` → `DONE` → Archive
+
+`BLOCKED` can return to `READY` when resolved. Reviewer rejection: `REVIEW` → `IN_PROGRESS`.
+
+## CLI commands
+
+```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
+```
+
+## OpenSpec folders
+
+Each item generates `openspec/changes/<slug>/` with `proposal.md`, `design.md`, `tasks.md`, `specs/` — compatible with Fission-AI OpenSpec layout (no external CLI required).
+
+## Agent phases
+
+| Phase | Agent |
+|-------|-------|
+| discover | repo-explorer |
+| design | architect |
+| test | tester |
+| implement | implementer |
+| review | reviewer |
+
+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.

package/presets/codex/AGENTS.md

@@ -114,6 +114,7 @@ When multiple signals apply, take the highest risk level. Do not average.
 | Codebase exploration | any         | `repo-explorer`                                     |
 | Code review          | any         | `reviewer`                                          |
 | Security review      | high        | `security-reviewer` → `reviewer`                    |
+| DDD→SDD→TDD pipeline | any         | `contract-builder` → `architect` → `implementer` → `tester` |
 
 ---
 
@@ -790,6 +791,62 @@ module, or identifying the impact radius of a change.
 
 ---
 
+### contract-builder
+
+**Role:** Defines API contracts, data shapes, and behavior specs before
+implementation. Produces OpenAPI specs, JSON Schema, or TypeScript interfaces
+that the implementer and tester use as the source of truth.
+
+**Use when:** New feature needs spec-before-implementation, API contract needs
+definition, or the DDD→SDD→TDD pipeline is triggered.
+
+**Permissions:**
+
+- read: `allow`
+- edit: `ask` (docs, ADRs, OpenAPI only)
+- bash: `deny`
+- network: `deny`
+
+**Does not:** Write implementation code. Modify production source files.
+
+**Model:** `{{MODEL_CODEX}}`
+
+**Deliverables:**
+
+- OpenAPI 3.x spec (`openapi.yaml` or `*-api.yaml`)
+- JSON Schema for request/response bodies
+- TypeScript interfaces for shared types
+- Contract test matrix (endpoint × status × shape)
+
+**Contract specification format:**
+
+```markdown
+## API Contract
+
+**Task**: [objective from Task Card]
+
+### Endpoints / Interfaces
+
+| Method | Path | Request | Response | Errors |
+| ------ | ---- | ------- | -------- | ------ |
+| POST | /api/v1/... | [schema ref] | [schema ref] | 400, 401, 422 |
+
+### Data shapes
+
+- `[TypeName]`: [field list with types and constraints]
+
+### Compatibility
+
+- Breaking changes: [yes/no — list if yes]
+- Versioning strategy: [URL prefix | header | none]
+
+### Contract tests required
+
+- [ ] [test description — request shape, response shape, error cases]
+```
+
+---
+
 ### goal-planner
 
 **Role:** Transforms an objective string into a YAML task graph with

package/presets/cursor/.cursorignore

@@ -0,0 +1,15 @@
+node_modules/
+dist/
+build/
+.gradle/
+*.lock
+.env*
+coverage/
+graphify-out/
+.next/
+.turbo/
+__pycache__/
+*.pyc
+.venv/
+target/
+vendor/