open-multi-agent-kit 0.80.7 → 0.80.8

package/docs/loadout-domains/ai-agent-ops.md

@@ -0,0 +1,94 @@
+# AI Agent Engineering & Ops (`ai-agent-ops`)
+
+> Inherited domain capability document. Auto-generated from `src/core/domain-loadouts.ts` — do not edit by hand.
+
+
+## Identity
+
+| field | value |
+|---|---|
+| id | `ai-agent-ops` |
+| authority | `write-scoped` |
+| tools | read, grep, find, ls, edit, write, bash |
+| command mode | `scoped-shell` |
+
+## Routing prompt
+
+> Prepended to the lane task prompt when the router selects this domain.
+
+```text
+DOMAIN: AI Agent Engineering & Ops. You are operating in an agent-systems capability lane.
+Prioritize eval-driven design, correct context engineering, and safe autonomy.
+
+SEQUENCE:
+1. Frame the system: agentic-engineering (eval-first, decomposition, cost-aware routing) + ai-first-engineering operating model.
+2. Context: context-engineering for prompt/command/skill/sub-agent construction; iterative-retrieval to solve the subagent context problem; prompt-optimizer before shipping prompts (test with a fresh subagent, RED-GREEN-REFACTOR).
+3. Build artifacts: create-agent / create-skill / create-hook for the harness; mcp-builder + mcp-server-patterns for MCP servers (correct tool schemas, Zod, stdio vs HTTP).
+4. Autonomy: autonomous-loops / continuous-agent-loop with quality gates + recovery; enterprise-agent-ops for long-lived workloads (observability, boundaries, lifecycle).
+5. Evaluate: eval-harness + agent-eval + agent-self-evaluation — never ship an agent change without a measured eval delta. nanoclaw-repl for interactive iteration.
+6. Orchestration: harness (team-architecture factory) for multi-agent topology; dispatching-parallel-agents / subagent-driven-development for parallel lanes; ralphinho-rfc-pipeline for DAG + merge queue.
+
+HARD RULES: every agent/skill change has an eval; prompts are versioned and tested, not vibe-edited; MCP servers validate inputs; autonomy is bounded by explicit stop conditions + stop-verify hook.
+```
+
+## Curated skills (23)
+
+- `agent-harness-construction`
+- `agentic-engineering`
+- `ai-first-engineering`
+- `autonomous-loops`
+- `continuous-agent-loop`
+- `enterprise-agent-ops`
+- `eval-harness`
+- `agent-self-evaluation`
+- `agent-eval`
+- `mcp-builder`
+- `mcp-server-patterns`
+- `prompt-optimizer`
+- `context-engineering`
+- `create-agent`
+- `create-skill`
+- `create-hook`
+- `iterative-retrieval`
+- `nanoclaw-repl`
+- `blueprint`
+- `ralphinho-rfc-pipeline`
+- `harness`
+- `subagent-driven-development`
+- `dispatching-parallel-agents`
+
+## Curated MCP servers (4)
+
+- `filesystem`
+- `memory`
+- `github`
+- `context7`
+
+## Curated hooks (4)
+
+- `session-context`
+- `precompact-checkpoint`
+- `stop-verify`
+- `subagent-stop-audit`
+
+## Routing triggers (17)
+
+| kind | pattern | weight |
+|---|---|---|
+| keyword | `agent` | 4 |
+| keyword | `mcp` | 6 |
+| keyword | `prompt` | 4 |
+| keyword | `skill` | 3 |
+| keyword | `hook` | 3 |
+| keyword | `harness` | 6 |
+| keyword | `orchestrat` | 5 |
+| keyword | `eval` | 5 |
+| keyword | `subagent` | 6 |
+| keyword | `tool` | 2 |
+| keyword | `loop` | 3 |
+| keyword | `context engineering` | 6 |
+| regex | `\b(model context protocol|llm agent|multi-?agent|agentic)\b` | 6 |
+| regex | `\b(token budget|context window|compaction|retrieval)\b` | 5 |
+| path | `.claude/agents` | 6 |
+| path | `.omk/` | 5 |
+| path | `SKILL.md` | 5 |

package/docs/loadout-domains/backend-api.md

@@ -0,0 +1,116 @@
+# Backend & API (`backend-api`)
+
+> Inherited domain capability document. Auto-generated from `src/core/domain-loadouts.ts` — do not edit by hand.
+
+
+## Identity
+
+| field | value |
+|---|---|
+| id | `backend-api` |
+| authority | `write-scoped` |
+| tools | read, grep, find, ls, edit, write, bash |
+| command mode | `scoped-shell` |
+
+## Routing prompt
+
+> Prepended to the lane task prompt when the router selects this domain.
+
+```text
+DOMAIN: Backend & API. You are operating in a backend/API capability lane.
+Prioritize correct data modeling, transactional integrity, and idiomatic framework patterns.
+
+SEQUENCE:
+1. Read the affected route/controller/service/repo and the schema in full first.
+2. For data changes: prefer the database-migrations skill (additive + backfill + expand/contract); never destructive in a single step. Validate with the framework verification skill (django-verification / laravel-verification / springboot-verification).
+3. Query work: apply postgres-patterns / supabase-postgres-best-practices (indexes, EXPLAIN, RLS). ClickHouse analytics use clickhouse-io.
+4. API shape: api-design skill for resource naming, status codes, pagination, error envelopes, versioning.
+5. Integrating LLMs: claude-api / codex-api skills for correct model ids, streaming, tool use, caching. Building an MCP server: mcp-server-patterns + mcp-build-mcp.
+6. Language idiom: use the matching *-patterns skill (python/golang/rust/kotlin/perl/cpp). Type-strict, no `any`.
+7. Security baseline: run security-review before claiming done; secrets never logged (protect-secrets hook enforces).
+
+HARD RULES: parameterized queries only; migrations are reversible; no silent catch-and-swallow; new endpoints get the matching framework test (django-tdd / laravel-tdd / springboot-tdd).
+```
+
+## Curated skills (33)
+
+- `backend-patterns`
+- `api-design`
+- `postgres-patterns`
+- `supabase`
+- `supabase-postgres-best-practices`
+- `database-migrations`
+- `clickhouse-io`
+- `redis`
+- `django-patterns`
+- `django-tdd`
+- `django-verification`
+- `laravel-patterns`
+- `laravel-tdd`
+- `laravel-verification`
+- `springboot-patterns`
+- `springboot-tdd`
+- `springboot-verification`
+- `jpa-patterns`
+- `python-patterns`
+- `python-testing`
+- `golang-patterns`
+- `golang-testing`
+- `kotlin-patterns`
+- `rust-patterns`
+- `java-coding-standards`
+- `cpp-coding-standards`
+- `perl-patterns`
+- `mcp-server-patterns`
+- `mcp-build-mcp`
+- `claude-api`
+- `codex-api`
+- `security-review`
+- `verification-loop`
+
+## Curated MCP servers (5)
+
+- `filesystem`
+- `supabase`
+- `github`
+- `context7`
+- `memory`
+
+## Curated hooks (4)
+
+- `pre-shell-guard`
+- `protect-secrets`
+- `typecheck-after-edit`
+- `npm-audit-summary`
+
+## Routing triggers (27)
+
+| kind | pattern | weight |
+|---|---|---|
+| keyword | `backend` | 5 |
+| keyword | `api` | 4 |
+| keyword | `endpoint` | 4 |
+| keyword | `database` | 5 |
+| keyword | `query` | 3 |
+| keyword | `migration` | 5 |
+| keyword | `schema` | 4 |
+| keyword | `server` | 3 |
+| keyword | `auth` | 3 |
+| keyword | `postgres` | 6 |
+| keyword | `supabase` | 6 |
+| keyword | `sql` | 5 |
+| keyword | `rest` | 3 |
+| keyword | `graphql` | 4 |
+| keyword | `orm` | 4 |
+| keyword | `django` | 6 |
+| keyword | `spring` | 6 |
+| keyword | `laravel` | 6 |
+| regex | `\b(route|controller|service|repository|model|dto)\b` | 3 |
+| extension | `.py` | 3 |
+| extension | `.go` | 5 |
+| extension | `.rs` | 5 |
+| extension | `.java` | 5 |
+| extension | `.kt` | 5 |
+| path | `api/` | 4 |
+| path | `server/` | 4 |
+| path | `migrations/` | 6 |

package/docs/loadout-domains/data-science.md

@@ -0,0 +1,100 @@
+# Data Science & Analysis (`data-science`)
+
+> Inherited domain capability document. Auto-generated from `src/core/domain-loadouts.ts` — do not edit by hand.
+
+
+## Identity
+
+| field | value |
+|---|---|
+| id | `data-science` |
+| authority | `execute-tests` |
+| tools | read, grep, find, ls, bash |
+| command mode | `tests-only` |
+
+## Routing prompt
+
+> Prepended to the lane task prompt when the router selects this domain.
+
+```text
+DOMAIN: Data Science & Analysis. You are operating in an analysis/modeling capability lane.
+Prioritize correct statistical reasoning, reproducibility, and honest uncertainty.
+
+SEQUENCE:
+1. Start with exploratory-data-analysis: shape, dtypes, missingness, distributions, basic sanity checks — never skip straight to modeling.
+2. Pick the dataframe engine by size: polars for in-memory speed, dask for larger-than-RAM. Do not reach for pandas by reflex.
+3. Visualization: seaborn/plotly for exploration, scientific-visualization for publication figures (colorblind-safe, correct error bars, journal styling).
+4. Modeling: scikit-learn for classical, pytorch-lightning for DL. State assumptions, then validate with statistical-analysis (right test, assumption checks, power). Bayesian work uses pymc; report with statsmodels.
+5. Interpretability: shap for global/local explanations; do not ship a black box without them.
+6. Reproducibility: fix seeds, pin versions, commit the exact data hash. Prefer scripts/functions over ad-hoc notebook cells for anything reused.
+
+HARD RULES: report effect size + CI, not just p-values; never train on test; never impute silently; notebooks are for exploration, modules are for production.
+```
+
+## Curated skills (25)
+
+- `exploratory-data-analysis`
+- `polars`
+- `dask`
+- `matplotlib`
+- `seaborn`
+- `plotly`
+- `scientific-visualization`
+- `scikit-learn`
+- `pytorch-lightning`
+- `transformers`
+- `networkx`
+- `pymc`
+- `statsmodels`
+- `sympy`
+- `statistical-analysis`
+- `shap`
+- `rdkit`
+- `biopython`
+- `scanpy`
+- `astropy`
+- `qiskit`
+- `deepchem`
+- `molecular-dynamics`
+- `hypothesis-generation`
+- `literature-review`
+
+## Curated MCP servers (3)
+
+- `filesystem`
+- `memory`
+- `context7`
+
+## Curated hooks (3)
+
+- `pre-shell-guard`
+- `protect-secrets`
+- `stop-verify`
+
+## Routing triggers (23)
+
+| kind | pattern | weight |
+|---|---|---|
+| keyword | `data` | 3 |
+| keyword | `analysis` | 4 |
+| keyword | `dataframe` | 5 |
+| keyword | `model` | 2 |
+| keyword | `training` | 4 |
+| keyword | `dataset` | 5 |
+| keyword | `statistics` | 5 |
+| keyword | `regression` | 4 |
+| keyword | `classification` | 4 |
+| keyword | `visualization` | 5 |
+| keyword | `plot` | 4 |
+| keyword | `notebook` | 5 |
+| keyword | `pandas` | 6 |
+| keyword | `polars` | 6 |
+| keyword | `numpy` | 5 |
+| keyword | `pytorch` | 6 |
+| keyword | `tensorflow` | 5 |
+| keyword | `scikit` | 6 |
+| keyword | `bayesian` | 5 |
+| regex | `\b(eda|ml|machine learning|inference|embedding)\b` | 5 |
+| extension | `.ipynb` | 7 |
+| path | `notebooks/` | 6 |
+| path | `models/` | 3 |

package/docs/loadout-domains/devops-infra.md

@@ -0,0 +1,85 @@
+# DevOps & Infrastructure (`devops-infra`)
+
+> Inherited domain capability document. Auto-generated from `src/core/domain-loadouts.ts` — do not edit by hand.
+
+
+## Identity
+
+| field | value |
+|---|---|
+| id | `devops-infra` |
+| authority | `write-scoped` |
+| tools | read, grep, find, ls, edit, write, bash |
+| command mode | `scoped-shell` |
+
+## Routing prompt
+
+> Prepended to the lane task prompt when the router selects this domain.
+
+```text
+DOMAIN: DevOps & Infrastructure. You are operating in a delivery/infra capability lane.
+Prioritize reproducible, reversible, observable changes.
+
+SEQUENCE:
+1. Read the Dockerfile / compose / workflow / IaC in full before editing.
+2. Containers: docker-patterns — pin base images, non-root user, multi-stage build, .dockerignore, healthchecks, least network egress.
+3. CI/CD: deployment-patterns for staging->prod, rollback strategy, secret handling. GitHub Actions touching LLM/agent steps must pass agentic-actions-auditor (you are in security-adjacent territory).
+4. Deploys: deploy-to-vercel / vercel-cli-with-tokens for Vercel; verification-loop after every deploy (health, smoke, rollback trigger).
+5. Database ops: database-migrations (expand/contract, zero-downtime) — coordinate with backend-api lane if schema semantics are unclear.
+6. Supply chain: npm-audit-summary hook surfaces dep risk; do not add lifecycle-script deps silently.
+
+HARD RULES: every deploy is reversible within one command; never bake secrets into images; lockfile/manifest changes are reviewed code; prefer idempotent steps. Read-only infra inspection uses read-only-shell; mutations stay scoped-shell.
+```
+
+## Curated skills (12)
+
+- `deployment-patterns`
+- `docker-patterns`
+- `database-migrations`
+- `continuous-agent-loop`
+- `enterprise-agent-ops`
+- `plankton-code-quality`
+- `verification-loop`
+- `deploy-to-vercel`
+- `vercel-cli-with-tokens`
+- `e2e-testing`
+- `clickhouse-io`
+- `security-review`
+
+## Curated MCP servers (3)
+
+- `github`
+- `filesystem`
+- `powershell-admin`
+
+## Curated hooks (4)
+
+- `npm-audit-summary`
+- `pre-shell-guard`
+- `protect-secrets`
+- `stop-verify`
+
+## Routing triggers (20)
+
+| kind | pattern | weight |
+|---|---|---|
+| keyword | `deploy` | 6 |
+| keyword | `deployment` | 6 |
+| keyword | `docker` | 6 |
+| keyword | `container` | 5 |
+| keyword | `kubernetes` | 6 |
+| keyword | `k8s` | 6 |
+| keyword | `ci` | 3 |
+| keyword | `pipeline` | 3 |
+| keyword | `infrastructure` | 5 |
+| keyword | `terraform` | 6 |
+| keyword | `vercel` | 6 |
+| keyword | `build` | 2 |
+| keyword | `release` | 4 |
+| keyword | `observability` | 5 |
+| regex | `\b(github actions|workflow|runner|helm|istio|nginx)\b` | 5 |
+| regex | `docker-?compose|\.ya?ml` | 3 |
+| path | `Dockerfile` | 7 |
+| path | `.github/workflows/` | 7 |
+| path | `docker-compose` | 7 |
+| extension | `.tf` | 7 |

package/docs/loadout-domains/docs-writing.md

@@ -0,0 +1,92 @@
+# Docs & Technical Writing (`docs-writing`)
+
+> Inherited domain capability document. Auto-generated from `src/core/domain-loadouts.ts` — do not edit by hand.
+
+
+## Identity
+
+| field | value |
+|---|---|
+| id | `docs-writing` |
+| authority | `write-scoped` |
+| tools | read, grep, find, ls, edit, write, bash |
+| command mode | `scoped-shell` |
+
+## Routing prompt
+
+> Prepended to the lane task prompt when the router selects this domain.
+
+```text
+DOMAIN: Docs & Technical Writing. You are operating in a writing capability lane.
+Prioritize clarity, accuracy, and the reader's time.
+
+SEQUENCE:
+1. Audience first: decide reader level, then choose register. Technical docs use write-concisely (cut hedging, active voice, concrete nouns).
+2. Collaborative/long docs: doc-coauthoring workflow (transfer context, iterate, verify it works for a reader).
+3. Prose type: article-writing for long-form; ux-writing for in-product microcopy/error/empty states; copywriting for marketing; internal-comms for status/incident/announcement.
+4. Academic: scientific-writing (IMRAD, citations, CONSORT/STROBE) + latex-posters; academic-pptx governs talk content/structure.
+5. Slides: slides-grab (plan->design->export) or frontend-slides for web decks; presentation-deck for stakeholder framing.
+6. Sync: docs-update-docs keeps READMEs/JSDoc/API docs current with code changes; keep CHANGELOG entries under [Unreleased].
+
+HARD RULES: no marketing fluff in technical docs; every code example is runnable; screenshots reflect current UI; brand-voice/brand-guidelines for tone consistency.
+```
+
+## Curated skills (20)
+
+- `article-writing`
+- `doc-coauthoring`
+- `write-concisely`
+- `ux-writing`
+- `copywriting`
+- `copy-editing`
+- `scientific-writing`
+- `latex-posters`
+- `academic-pptx`
+- `slides-grab`
+- `frontend-slides`
+- `presentation-deck`
+- `case-study`
+- `design-rationale`
+- `internal-comms`
+- `docs-update-docs`
+- `brand-voice`
+- `brand-guidelines`
+- `theme-factory`
+- `web-asset-generator`
+
+## Curated MCP servers (3)
+
+- `filesystem`
+- `memory`
+- `obsidian`
+
+## Curated hooks (3)
+
+- `session-context`
+- `precompact-checkpoint`
+- `pre-shell-guard`
+
+## Routing triggers (20)
+
+| kind | pattern | weight |
+|---|---|---|
+| keyword | `documentation` | 6 |
+| keyword | `docs` | 5 |
+| keyword | `readme` | 6 |
+| keyword | `write` | 2 |
+| keyword | `article` | 5 |
+| keyword | `blog` | 4 |
+| keyword | `guide` | 4 |
+| keyword | `tutorial` | 5 |
+| keyword | `slides` | 5 |
+| keyword | `presentation` | 5 |
+| keyword | `changelog` | 6 |
+| keyword | `microcopy` | 5 |
+| keyword | `manuscript` | 5 |
+| regex | `\b(prose|rewrite|edit copy|proofread)\b` | 5 |
+| extension | `.md` | 4 |
+| extension | `.mdx` | 4 |
+| extension | `.tex` | 6 |
+| extension | `.pptx` | 6 |
+| path | `docs/` | 5 |
+| path | `CHANGELOG` | 6 |

package/docs/loadout-domains/frontend-ui.md

@@ -0,0 +1,128 @@
+# Frontend & UI (`frontend-ui`)
+
+> Inherited domain capability document. Auto-generated from `src/core/domain-loadouts.ts` — do not edit by hand.
+
+
+## Identity
+
+| field | value |
+|---|---|
+| id | `frontend-ui` |
+| authority | `write-scoped` |
+| tools | read, grep, find, ls, edit, write, bash |
+| command mode | `scoped-shell` |
+
+## Routing prompt
+
+> Prepended to the lane task prompt when the router selects this domain.
+
+```text
+DOMAIN: Frontend & UI. You are operating in a frontend/UI capability lane.
+Prioritize visual craft, correct component composition, and accessibility.
+
+SEQUENCE:
+1. Read the target component(s)/page(s) in full before editing. Do not edit blind from search snippets.
+2. Identify the design system in use (Tailwind v4 / shadcn/ui / CSS modules / vanilla). Match it exactly; never introduce a second system.
+3. For visual work: drive iteration with the chrome-devtools or playwright MCP (navigate, screenshot, diff) — do not claim "looks good" without a captured frame.
+4. Accessibility: run the fixing-accessibility + contrast-checker + use-of-color skills. Every interactive element needs a reachable name, visible focus, and AA contrast.
+5. Motion: prefer the transitions-dev / animate / 12-principles-of-animation skills; gate heavy effects behind fix-motion-performance so animation never blocks the main thread.
+6. Prefer composition over boolean-prop sprawl (vercel-composition-patterns). Keep components small; extract when a prompt would exceed ~150 lines of spec.
+7. Before claiming done: typecheck-after-edit hook must pass, plus the web-quality-audit skill (perf/a11y/SEO/best-practices).
+
+HARD RULES: no inline styles when a token/utility exists; oklch tokens for color; mobile-first responsive; real content over placeholders; pixel-match the target first, customize later.
+```
+
+## Curated skills (48)
+
+- `frontend-design`
+- `frontend-ui-engineering`
+- `frontend-patterns`
+- `baseline-ui`
+- `impeccable`
+- `shape`
+- `make-interfaces-feel-better`
+- `transitions-dev`
+- `animate`
+- `polish`
+- `layout`
+- `typeset`
+- `colorize`
+- `oklch-skill`
+- `high-end-visual-design`
+- `minimalist-ui`
+- `design-taste-frontend`
+- `redesign-existing-projects`
+- `web-design-guidelines`
+- `fixing-accessibility`
+- `contrast-checker`
+- `use-of-color`
+- `fixing-motion-performance`
+- `12-principles-of-animation`
+- `to-spring-or-not-to-spring`
+- `mastering-animate-presence`
+- `pseudo-elements`
+- `shadcn`
+- `next-best-practices`
+- `next-cache-components`
+- `vercel-react-best-practices`
+- `vercel-composition-patterns`
+- `vue-best-practices`
+- `vue`
+- `svelte-code-writer`
+- `react-pdf`
+- `remotion-best-practices`
+- `web-quality-audit`
+- `audit-and-fix`
+- `image-to-code`
+- `visual-ralph`
+- `gstack-design-review`
+- `gstack-design-html`
+- `gstack-design-shotgun`
+- `clone-website`
+- `ui-design-brain`
+- `interface-design`
+- `emil-design-eng`
+
+## Curated MCP servers (4)
+
+- `chrome-devtools`
+- `playwright`
+- `filesystem`
+- `context7`
+
+## Curated hooks (3)
+
+- `typecheck-after-edit`
+- `pre-shell-guard`
+- `protect-secrets`
+
+## Routing triggers (26)
+
+| kind | pattern | weight |
+|---|---|---|
+| keyword | `ui` | 3 |
+| keyword | `frontend` | 5 |
+| keyword | `component` | 3 |
+| keyword | `css` | 4 |
+| keyword | `tailwind` | 5 |
+| keyword | `responsive` | 4 |
+| keyword | `layout` | 3 |
+| keyword | `design` | 3 |
+| keyword | `accessibility` | 4 |
+| keyword | `a11y` | 4 |
+| keyword | `animation` | 4 |
+| keyword | `pixel-perfect` | 5 |
+| keyword | `landing page` | 5 |
+| keyword | `redesign` | 4 |
+| keyword | `button` | 2 |
+| keyword | `modal` | 2 |
+| keyword | `shadcn` | 5 |
+| keyword | `clone` | 3 |
+| regex | `\b(react|vue|svelte|next\.?js|nuxt)\b` | 4 |
+| regex | `\b(tailwind|css|styled|emotion|radix)\b` | 4 |
+| extension | `.vue` | 6 |
+| extension | `.tsx` | 4 |
+| extension | `.jsx` | 4 |
+| extension | `.css` | 5 |
+| path | `components/` | 4 |
+| path | `app/page` | 3 |

package/docs/loadout-domains/general.md

@@ -0,0 +1,62 @@
+# General (fallback) (`general`)
+
+> Inherited domain capability document. Auto-generated from `src/core/domain-loadouts.ts` — do not edit by hand.
+
+_Fallback profile — selected when no domain clears the weak threshold._
+
+
+## Identity
+
+| field | value |
+|---|---|
+| id | `general` |
+| authority | `write-scoped` |
+| tools | read, grep, find, ls, edit, write, bash |
+| command mode | `scoped-shell` |
+
+## Routing prompt
+
+> Prepended to the lane task prompt when the router selects this domain.
+
+```text
+DOMAIN: General. No specific domain scored above threshold, so apply broad engineering hygiene.
+
+SEQUENCE:
+1. understand-chat / brainstorming to confirm intent if ambiguous; otherwise read the target in full.
+2. coding-standards for idiom; systematic-debugging for any defect (reproduce -> isolate -> fix -> verify, never guess).
+3. verification-before-completion: run the real check command and show output before claiming done.
+4. receiving-code-review: treat feedback technically, verify before applying.
+
+HARD RULES: read before edit; smallest safe change; verify with evidence; ask one concise question if truly blocked.
+```
+
+## Curated skills (7)
+
+- `coding-standards`
+- `verification-before-completion`
+- `systematic-debugging`
+- `receiving-code-review`
+- `context-engineering`
+- `understand-chat`
+- `brainstorming`
+
+## Curated MCP servers (3)
+
+- `filesystem`
+- `context7`
+- `memory`
+
+## Curated hooks (3)
+
+- `pre-shell-guard`
+- `protect-secrets`
+- `stop-verify`
+
+## Routing triggers (4)
+
+| kind | pattern | weight |
+|---|---|---|
+| keyword | `refactor` | 2 |
+| keyword | `fix` | 2 |
+| keyword | `implement` | 2 |
+| keyword | `function` | 1 |