cc-codeconductor 1.0.0 → 1.2.0

package/presets/opencode/commands/cc-spec-mutation.md

@@ -0,0 +1,190 @@
+---
+description: >-
+  Spec-locked TDD with a mutation-testing gate — refine the intent
+  into an immutable Gherkin contract (SHA-256 frozen), implement under the
+  three laws of TDD, pass a judge audit, and merge only if every mutant dies.
+---
+
+# Spec-Mutation — Hard Spec → TDD → Judge → Mutation Gate
+
+Scope: $ARGUMENTS
+
+Describe what behavior you want to implement. Include:
+
+- The function, method, or feature to implement
+- The expected behavior (inputs, outputs, invariants, edge cases)
+- The allowed file scope (production files that may change)
+- The test command for the affected suite (e.g. `pytest tests/test_billing.py`)
+
+---
+
+## Step 0 — CCEP Bootstrap
+
+Command: `spec-mutation` (fixed for this workflow — do not infer from user text)
+
+1. Run: `npx cc-codeconductor ccep parse --command spec-mutation "$ARGUMENTS" --output json`
+2. Run: `npx cc-codeconductor ccep resolve --command spec-mutation "$ARGUMENTS" --output json`
+3. Run: `npx cc-codeconductor ccep profile spec-mutation --output json`
+4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command spec-mutation --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+5. Delegate to subagents using compiled CCEP prompts — never forward raw `$ARGUMENTS` to planners.
+   Canonical delivery order is test-before-implement whenever both phases apply.
+
+---
+
+## Step 0b — OpenSpec quality gates
+
+If `openspec status` reports an active change folder:
+
+1. Run: `npx cc-codeconductor openspec validate --output json`
+2. Run: `npx cc-codeconductor openspec analyze --output json`
+3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
+4. Next command spelling on this runner: `/cc-spec-mutation`
+
+Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
+
+---
+
+## Contract
+
+The Gherkin specification is the **immutable contract** of the system. No code
+merges unless it survives intentional source mutations. The loop is closed:
+
+```
+[Human + spec_partner] ──> [gherkin_author] ──> [Test Freeze: SHA-256]
+                                                       │
+┌──────────────────────────────────────────────────────┘
+▼
+[tdd_craftsman] <───────────────┐ (surviving mutant)
+   (Red-Green-Refactor)         │
+        │                       │
+        ▼                       │
+     [judge] ───────────> [mutation_testing] ───> [Safe Merge]
+```
+
+Role mapping onto Conductor Agents (AGENTS.md):
+
+| Workflow role      | Conductor Agent   | Deliverable                                |
+| ------------------ | ----------------- | ------------------------------------------ |
+| `craftsman_lead`   | `orchestrator`    | Routed Task Cards, per-stage scorecards    |
+| `spec_partner`     | `task-coach`      | Spec draft with invariants and boundaries  |
+| `gherkin_author`   | `contract-builder`| Strict `.feature` file (Given/When/Then)   |
+| `tdd_craftsman`    | `tester` → `implementer` | Failing test, then minimal production code |
+| `judge`            | `reviewer`        | Binary verdict (PASS/REJECT) with scoring  |
+| `mutation_testing` | `tester` (runner) | Killed/survived mutant report              |
+
+## Stage 1 — Interactive refinement (`spec_partner` / task-coach)
+
+Do not jump to implementation. Apply Socratic questioning to the initial intent:
+
+- Preconditions, postconditions, and edge cases.
+- Invariant matrix: what must always be true.
+- Scope boundaries: explicit `Scope / Files` and `Scope / Out` for the Task Card.
+
+Stop gate: human confirms the draft before formalization.
+
+## Stage 2 — Hard Spec formalization (`gherkin_author` / contract-builder)
+
+Formalize the agreed draft into `specs/<task>.feature` using strict Gherkin:
+
+- No vague language ("must respond fast" is forbidden — use measurable Then steps).
+- Every scenario declares preconditions (`Given`), actions (`When`), and
+  observable states (`Then`).
+- Once the human approves the `.feature`, freeze it:
+
+```bash
+shasum -a 256 specs/<task>.feature tests/ > .codeconductor/tasks/<task_id>.lock
+```
+
+From this point `specs/` and `tests/` are **read-only** for implementation
+agents. Before every later gate, recompute the hash; any single-byte difference
+aborts the pipeline with scorecard 0 (Specification Gaming).
+
+## Stage 3 — TDD under the three laws (`tdd_craftsman`)
+
+Delegates to the `/cc-tdd-cycle` state machine (`tddCycleStateMachine` in
+`domain/loop`). Evidence must be captured with `captureTddSuiteEvidence` — do
+not hand-edit JSON under `.codeconductor/evidence/`.
+
+1. **Law 1 (RED):** no production code except to make a failing test pass. A
+   compile error from a missing interface counts as a failure.
+2. **Law 2:** write exactly one failing assertion or scenario at a time.
+3. **Law 3 (GREEN):** write only the minimal production code to pass. No
+   speculative code, no preventive heuristics, stdlib-first.
+
+Hard rule: any write attempt against `specs/` or `tests/` during GREEN/REFACTOR
+is a harness violation — stop execution and report.
+
+## Stage 4 — Judge audit (`judge` / reviewer)
+
+Deterministic gates before spending compute on mutation:
+
+- Clean compile / diagnostics exit code 0.
+- Traceability: every Gherkin step maps to an implemented test step.
+- Scope Gaming audit: `git diff --name-only` must match the Task Card
+  `Scope / Files` exactly. Relaxed types, weakened assertions, or out-of-scope
+  edits → REJECT with findings.
+
+Verdict is binary: PASS continues to the mutation gate; REJECT returns to the
+`implement` phase with the findings attached.
+
+## Stage 5 — Mutation gate (`mutation_testing`)
+
+Run the deterministic AST mutator shipped with this preset:
+
+```bash
+python3 presets/shared/mutation_runner.py \
+  --target <production_file.py> \
+  --test-command "<test command>" \
+  --spec-folder specs
+```
+
+The runner applies deterministic operator mutations (`>` → `<=`, `==` → `!=`,
+`is` → `is not`, …) one at a time, re-runs the suite per mutant, and restores
+the original source unconditionally (`finally` rollback).
+
+- **Mutant killed (tests fail):** the suite detects the corruption. Continue.
+- **Mutant survived (tests pass):** the tests are blind to this branch. The
+  runner writes `specs/handover.md` + appends to
+  `specs/implementation-summary.md` and exits with code **2**.
+
+Non-Python stacks: substitute Stryker (JS/TS), PITest (JVM), or Mutmut
+(Python full-suite) with the same contract — 100% kill rate or hands-off.
+
+### Hands-off protocol (exit code 2)
+
+1. Do NOT modify production code to "fix" a surviving mutant.
+2. Route back to `tdd_craftsman` with `specs/handover.md` as input: write the
+   missing failing test (Law 1 & 2) that asserts the mutated branch.
+3. Re-run stages 3–5.
+
+### Circuit breaker (max 3 loops)
+
+The orchestrator keeps a persistent counter per Task Card. If the
+`tdd_craftsman ↔ mutation_testing` loop does not reach a 100% kill rate after
+**3 iterations**:
+
+- Cancel active subagents (stop token/context spend).
+- `git checkout -- <scope>` rollback to the last clean state.
+- Scorecard: `STATUS = BLOCKED`; escalate to a human operator. The branch stays
+  frozen until human arbitration.
+
+## Guardrails (harness-enforced, not prompt-enforced)
+
+- **Test Freezing:** SHA-256 of `specs/` + `tests/` stored in
+  `.codeconductor/tasks/<task_id>.lock`; hash mismatch aborts the pipeline.
+- **Scope Guardian:** `fs_write`/`fs_patch` paths are validated against the Task
+  Card `Scope / Files`; path escapes (`../`) and critical files (`**/.env*`,
+  `**/credentials*`, infrastructure roots) are denied per `policy.yml`.
+- **RBAC per role:** `gherkin_author` writes only `specs/`; `tdd_craftsman`
+  reads specs/tests and writes only scoped `src/`; `judge` and
+  `mutation_testing` are read-only except the runner's rolled-back patch.
+- **Worktree isolation:** run the whole flow in a dedicated `git worktree`;
+  protected branches (`main`, `master`, `develop`) are never touched.
+
+## Completion criteria
+
+- [ ] `.feature` approved and frozen (SHA-256 lock file exists and matches).
+- [ ] RED → GREEN → REFACTOR evidence captured per phase.
+- [ ] Judge verdict PASS (compile clean, traceability complete, scope clean).
+- [ ] Mutation runner exits 0 with `total_mutants_killed == total_points`.
+- [ ] Scorecard records the kill rate and iteration count (≤ 3).

package/presets/opencode/commands/cc-tdd-cycle.md

@@ -30,6 +30,20 @@ Command: `tdd-cycle` (fixed for this workflow — do not infer from user text)
 
 ---
 
+## Step 0b — OpenSpec quality gates
+
+If `openspec status` reports an active change folder:
+
+1. Run: `npx cc-codeconductor openspec validate --output json`
+2. Run: `npx cc-codeconductor openspec analyze --output json`
+3. If analyze `stop` is true or any finding is CRITICAL, stop. Do not delegate to implementer.
+4. Next command spelling on this runner: `/cc-tdd-cycle`
+
+Local development: `bun run dev <same argv>`. Published package: `npx cc-codeconductor`.
+
+---
+
+
 ## Before you begin — mandatory pre-check
 
 This command enforces strict TDD discipline. The three phases are sequential and

package/presets/opencode/gates/pre-commit/GATE.md

@@ -1,6 +1,6 @@
-# Pre-commit Gate: Typecheck and Test
+# Pre-commit Gate: Typecheck, Lint, and Test
 
-Este gate instala un hook `pre-commit` que ejecuta `bun run typecheck` y `bun run test` antes de permitir commits en el repositorio. Si cualquiera de estos comandos falla, el commit es bloqueado.
+Este gate instala un hook `pre-commit` que ejecuta `bun run typecheck`, `bun run lint` y `bun run test` antes de permitir commits en el repositorio. Si cualquiera de estos comandos falla, el commit es bloqueado.
 
 ## Cuándo usar
 
@@ -63,6 +63,7 @@ mkdir -p "$GIT_DIR/hooks"
 cat > "$HOOK_PATH" << 'HOOK_EOF'
 #!/bin/bash
 bun run typecheck || exit 1
+bun run lint || exit 1
 bun run test || exit 1
 HOOK_EOF
 
@@ -78,7 +79,7 @@ echo "Pre-commit hook installed successfully."
 - **Resolución dinámica de git dir**: Usa `git rev-parse --git-dir` para localizar el directorio correcto, incluso en worktrees.
 - **Detección de conflictos**: Si Husky o lint-staged ya está en `package.json`, el script avisa y no instala para evitar conflictos.
 - **Protección de hooks existentes**: Si ya existe un `.git/hooks/pre-commit`, el script no lo sobrescribe.
-- **Solo Bun**: El hook ejecuta `bun run typecheck` y `bun run test`. Asegúrate de que estos scripts están definidos en `package.json`.
+- **Solo Bun**: El hook ejecuta `bun run typecheck`, `bun run lint` y `bun run test`. Asegúrate de que estos scripts están definidos en `package.json`.
 
 ## Verificación
 
@@ -121,7 +122,7 @@ Verifica que el hook es ejecutable:
 
     chmod +x .git/hooks/pre-commit
 
-Verifica que `bun run typecheck` y `bun run test` existen en `package.json`:
+Verifica que `bun run typecheck`, `bun run lint` y `bun run test` existen en `package.json`:
 
     cat package.json | grep -A 5 '"scripts"'
 

package/presets/opencode/opencode.jsonc

@@ -1,6 +1,6 @@
 {
   "$schema": "https://opencode.ai/config.json",
-  "model": "opencode-go/qwen3.7-max",
+  "model": "opencode-go/qwen3.7-plus",
   "permission": {
     "*": "ask",
     "read": {

package/presets/opencode/prompts/v1.0.0/architect.md

@@ -257,3 +257,9 @@ Rules under CCEP-1:
 - Never approve your own plan — the human approves before implementation starts.
 - If scope expands during design, flag it as a separate task, not an extension
   of the current one.
+
+## Composition
+
+Invoke via `/cc-feature`, `/cc-openspec`, or the orchestrator. Do not invoke
+other agents. If an OpenSpec change folder is active, invoke skill `openspec`
+and run `openspec analyze --output json` before implementation is allowed.

package/presets/opencode/prompts/v1.0.0/implementer.md

@@ -226,3 +226,10 @@ tests. On **REJECT**, stop and escalate to the orchestrator.
 - Never modify the Technical Plan — if the plan is wrong, escalate to
   `architect` via the orchestrator.
 - Never commit without human confirmation.
+
+## Composition
+
+Invoke via `/cc-feature`, `/cc-fix`, `/cc-tdd-cycle`, or the orchestrator.
+Do not invoke other agents. Invoke skill `testing-tdd`.
+Deliverable is incomplete without a passing suite and runner TDD evidence when
+TDD is required. Scorecard: `bun run dev scorecard create --from-diff`.

package/presets/opencode/prompts/v1.0.0/reviewer.md

@@ -293,3 +293,9 @@ Invoke skill `evaluation` and run `scorecard record` with agent `reviewer`, mode
 - Never issue vague findings ("this could be better") — every finding must name
   the exact location and the specific required action.
 - Never run `git push` or `git commit`.
+
+## Composition
+
+Invoke via `/cc-review` or the orchestrator. Do not invoke other agents.
+Invoke skill `evaluation`. Deliverable is incomplete without
+`scorecard create --from-diff` and a recorded PASS|REVISE|REJECT.

package/presets/opencode/prompts/v1.0.0/tester.md

@@ -296,3 +296,9 @@ and confirmed failing; list the failing test paths in `artifacts` so the
 - Never mock real behavior that could be tested with an in-memory alternative.
 - Never declare coverage complete when any acceptance criterion lacks a test.
 - Never run `git push` or `git commit`.
+
+## Composition
+
+Invoke via `/cc-tdd-cycle`, `/cc-feature`, or the orchestrator (test before
+implement). Do not invoke other agents. Invoke skill `testing-tdd`.
+Deliverable is incomplete without `captureTddSuiteEvidence` when TDD is required.

package/presets/opencode/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

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

@@ -1,6 +1,65 @@
 ---
 name: evaluation
-description: Scorecard, outcomes, model profiles. Use with /cc-scorecard.
+description:
+  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.
 ---
 
-See `presets/claude/skills/evaluation/SKILL.md` for full evaluation workflow.
+# Evaluation
+
+## Overview
+
+A scorecard measures the deliverable against eight weighted criteria. Spec
+quality checklists are reviewer-owned. "Seems right" is not a verdict.
+
+Pass threshold: weighted score >= 2.0 and no criterion at 0.
+
+## 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
+```
+
+`openspec analyze` can auto-suggest `acceptance` / `tests` on `--from-diff`.
+Archive needs PASS when review is required.
+
+Outcomes append to `.codeconductor/evaluation/outcomes.jsonl`.
+
+## Common Rationalizations
+
+| 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. |
+
+## Red Flags
+
+- 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`
+
+## Verification
+
+- [ ] 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/opencode/skills/openspec/SKILL.md

@@ -1,50 +1,66 @@
 ---
 name: openspec
 description:
-  OpenSpec backlog format, state machine, and delivery workflow for CodeConductor.
-  Use when running /cc-openspec or editing BACKLOG.md.
+  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
 
-## BACKLOG.md contract
+## Overview
 
-`BACKLOG.md` at repo root is the operational queue. Required sections:
+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.
 
-- `## Global` — Product, Strategy, Policy, Review required, TDD required
-- `## Items` — active backlog entries
-- `## Archive` — completed entries (do not re-execute)
+## When to Use
 
-Each item: `### BC-001 | Short title` with Priority (P0–P3), Status, Type, Depends on, Description, Scope, Out of scope, Acceptance (measurable checklist).
+- `/cc-openspec` or `openspec next` / `plan` / `done` / `archive`
+- An item is `READY` or later and must move through the state machine
 
-## Status machine
+**NOT** for creating `BACKLOG.md` (use skill `backlog`) or for stack-specific
+coding rules.
 
-`TODO` → `READY` → `PLANNED` → `IN_PROGRESS` → `REVIEW` → `DONE` → Archive
+## Process
 
-`BLOCKED` can return to `READY` when resolved. Reviewer rejection: `REVIEW` → `IN_PROGRESS`.
+Local CLI is `bun run dev`. Published package is `npx cc-codeconductor`.
 
-## CLI commands
+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.
 
-```bash
-npx cc-codeconductor openspec validate
-npx cc-codeconductor openspec scan
-npx cc-codeconductor openspec plan BC-001
-npx cc-codeconductor openspec status
-npx cc-codeconductor openspec next
-```
+Status machine: `TODO` → `READY` → `PLANNED` → `IN_PROGRESS` → `REVIEW` → `DONE`
+→ Archive. `BLOCKED` returns to `READY`. Reviewer rejection: `REVIEW` →
+`IN_PROGRESS`.
 
-## OpenSpec folders
+## Common Rationalizations
 
-Each item generates `openspec/changes/<slug>/` with `proposal.md`, `design.md`, `tasks.md`, `specs/`.
+| 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. |
 
-## Agent phases
+## Red Flags
 
-| Phase | Agent |
-|-------|-------|
-| discover | repo-explorer |
-| design | architect |
-| test | tester |
-| implement | implementer |
-| review | reviewer |
+- Implementing while analyze reports CRITICAL
+- Archive without a PASS scorecard when review is required
+- Acceptance like "improve UX" with no measurable check
 
-When Global `TDD required: yes`, test runs before implement.
+## Verification
+
+- [ ] `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/opencode/skills/security-ai-llm/SKILL.md

@@ -0,0 +1,43 @@
+---
+name: security-ai-llm
+description: >
+  Harden LLM and agent integrations you operate: prompt injection, tool allowlists, secret leakage, and supply-chain of models. Defensive only.
+---
+
+# AI / LLM Security
+
+## Authorization
+
+Use this skill only with **explicit written authorization** for a named
+scope (systems, environments, and time window). If authorization is missing,
+expired, or the request is for someone else's systems, **stop**.
+
+This skill is **defensive and owner-authorized**. It does not authorize
+offensive cyber operations.
+
+## Do
+
+- Treat model output as untrusted; never exec it without a schema
+- Allowlist tools and paths; contain file writes
+- Keep secrets out of prompts and logs
+
+## Do not
+
+- Help jailbreak third-party products or steal model weights
+- Log raw user PII to prompt-debug stores
+
+- Do not produce exploit payloads, malware, or attack procedures.
+
+## How to Use
+
+Load this skill from `/cc-security` when the Task Card domain is `security-ai-llm`.
+Example prompts:
+
+- `Review our agent tool runner for path traversal and unbounded shell.`
+- `Add tests that a prompt cannot make the bot dump .env.`
+
+## Integration
+
+- Workflow: `/cc-security` (CCEP command `security`)
+- Existing OWASP application-security skill remains `security` (not this id)
+- High-risk changes still require `security-reviewer`

package/presets/opencode/skills/security-blue-team/SKILL.md

@@ -0,0 +1,43 @@
+---
+name: security-blue-team
+description: >
+  Improve detections, hardening, and response for the estate you defend. Detection-as-code and control design, not offense.
+---
+
+# Blue Team Defense
+
+## Authorization
+
+Use this skill only with **explicit written authorization** for a named
+scope (systems, environments, and time window). If authorization is missing,
+expired, or the request is for someone else's systems, **stop**.
+
+This skill is **defensive and owner-authorized**. It does not authorize
+offensive cyber operations.
+
+## Do
+
+- Tune detections for true positives; document exceptions
+- Pair every new control with a test or canary
+- Share hunt hypotheses with IR, not with the public internet
+
+## Do not
+
+- Disable EDR or logging to 'reduce noise' without a ticket
+- Copy attacker malware into production 'for training'
+
+- Do not produce exploit payloads, malware, or attack procedures.
+
+## How to Use
+
+Load this skill from `/cc-security` when the Task Card domain is `security-blue-team`.
+Example prompts:
+
+- `We missed a token-replay. Propose a detection plus a unit test for the API gateway.`
+- `Harden CI: pin actions, require reviews on workflows that deploy.`
+
+## Integration
+
+- Workflow: `/cc-security` (CCEP command `security`)
+- Existing OWASP application-security skill remains `security` (not this id)
+- High-risk changes still require `security-reviewer`

package/presets/opencode/skills/security-cloud/SKILL.md

@@ -0,0 +1,43 @@
+---
+name: security-cloud
+description: >
+  Harden IAM, storage, keys, and org policies in cloud accounts you administer. Focus on identity, logging, and public-exposure controls.
+---
+
+# Cloud Security
+
+## Authorization
+
+Use this skill only with **explicit written authorization** for a named
+scope (systems, environments, and time window). If authorization is missing,
+expired, or the request is for someone else's systems, **stop**.
+
+This skill is **defensive and owner-authorized**. It does not authorize
+offensive cyber operations.
+
+## Do
+
+- Prefer roles over long-lived keys; require MFA on human admins
+- Block public buckets and overly broad IAM `*` unless justified
+- Turn on cloud audit logs and retain them per policy
+
+## Do not
+
+- Disable logging or GuardDuty/Security Command Center 'to save cost' without a recorded exception
+- Share account credentials in chat or tickets
+
+- Do not produce exploit payloads, malware, or attack procedures.
+
+## How to Use
+
+Load this skill from `/cc-security` when the Task Card domain is `security-cloud`.
+Example prompts:
+
+- `Audit this AWS account's IAM: unused keys, admin wildcards, and public S3.`
+- `Write a policy-as-code check that fails CI if a bucket ACL is public.`
+
+## Integration
+
+- Workflow: `/cc-security` (CCEP command `security`)
+- Existing OWASP application-security skill remains `security` (not this id)
+- High-risk changes still require `security-reviewer`