~ / rigs / Lukk17 / agent-standards

Lukk17/agent-standards

One git checkout drops a shared AI coding setup (skills, subagents, MCP servers, OpenSpec scaffolding) into any project, across Claude Code, Kilo, OpenCode, Codex, and Copilot.

share on X
ARCHETYPE
MCP Hoarder
Six or more MCP servers wired in. Every tool, always in context.
CONTEXT TAX · EVERY TURN
~47.5k tokens
Context hog · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add --transport http context7 https://mcp.context7.com/mcp -H 'CONTEXT7_API_KEY: YOUR_VALUE'
$ claude mcp add mongodb -- npx -y mongodb-mcp-server@latest --readOnly --connectionString ${MONGODB_URL:-mongodb://localhost:27017}
$ claude mcp add grafana -e GRAFANA_SERVICE_ACCOUNT_<redacted> -e GRAFANA_URL=YOUR_GRAFANA_URL -- uvx mcp-grafana
$ claude mcp add playwright -- npx @playwright/mcp@latest
$ claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest
$ claude mcp add redis -- uvx --from redis-mcp-server@latest redis-mcp-server --url ${REDIS_URL:-redis://localhost:6379/0}
$ claude mcp add sonarqube -e SONARQUBE_<redacted> -e SONARQUBE_URL=YOUR_SONARQUBE_URL -- docker run --init --pull=always -i --rm -e SONARQUBE_TOKEN -e SONARQUBE_URL mcp/sonarqube
$ claude mcp add n8n -e N8N_<redacted> -e N8N_API_URL=YOUR_N8N_API_URL -- npx n8n-mcp
$ npx degit Lukk17/agent-standards/.claude ./rig-agent-standards  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ claude mcp add --transport http context7 https://mcp.context7.com/mcp -H 'CONTEXT7_API_KEY: YOUR_VALUE'
$ claude mcp add mongodb -- npx -y mongodb-mcp-server@latest --readOnly --connectionString ${MONGODB_URL:-mongodb://localhost:27017}
$ claude mcp add grafana -e GRAFANA_SERVICE_ACCOUNT_<redacted> -e GRAFANA_URL=YOUR_GRAFANA_URL -- uvx mcp-grafana
$ claude mcp add playwright -- npx @playwright/mcp@latest
$ claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest
$ claude mcp add redis -- uvx --from redis-mcp-server@latest redis-mcp-server --url ${REDIS_URL:-redis://localhost:6379/0}
$ claude mcp add sonarqube -e SONARQUBE_<redacted> -e SONARQUBE_URL=YOUR_SONARQUBE_URL -- docker run --init --pull=always -i --rm -e SONARQUBE_TOKEN -e SONARQUBE_URL mcp/sonarqube
$ claude mcp add n8n -e N8N_<redacted> -e N8N_API_URL=YOUR_N8N_API_URL -- npx n8n-mcp
$ npx degit Lukk17/agent-standards/.agents/skills/agentic-engineering .claude/skills/agentic-engineering
$ npx degit Lukk17/agent-standards/.agents/skills/ai-regression-testing .claude/skills/ai-regression-testing
$ npx degit Lukk17/agent-standards/.agents/skills/angular .claude/skills/angular
$ npx degit Lukk17/agent-standards/.agents/skills/ansible .claude/skills/ansible
$ npx degit Lukk17/agent-standards/.agents/skills/api-design .claude/skills/api-design
$ npx degit Lukk17/agent-standards/.agents/skills/architecture-decision-records .claude/skills/architecture-decision-records
$ npx degit Lukk17/agent-standards/.agents/skills/ascend-memory .claude/skills/ascend-memory
$ npx degit Lukk17/agent-standards/.agents/skills/ascend-web-hunter .claude/skills/ascend-web-hunter
$ npx degit Lukk17/agent-standards/.agents/skills/audio-scribe .claude/skills/audio-scribe
$ npx degit Lukk17/agent-standards/.agents/skills/automation-inventory .claude/skills/automation-inventory
$ npx degit Lukk17/agent-standards/.agents/skills/backend-patterns .claude/skills/backend-patterns
$ npx degit Lukk17/agent-standards/.agents/skills/bash .claude/skills/bash
$ npx degit Lukk17/agent-standards/.agents/skills/build-dependency-management .claude/skills/build-dependency-management
$ npx degit Lukk17/agent-standards/.agents/skills/code-formatter .claude/skills/code-formatter
$ npx degit Lukk17/agent-standards/.agents/skills/code-reviewer .claude/skills/code-reviewer
$ npx degit Lukk17/agent-standards/.agents/skills/coding-standards .claude/skills/coding-standards
$ npx degit Lukk17/agent-standards/.agents/skills/dart-flutter-patterns .claude/skills/dart-flutter-patterns
$ npx degit Lukk17/agent-standards/.agents/skills/database-migrations .claude/skills/database-migrations
$ npx degit Lukk17/agent-standards/.agents/skills/deployment-patterns .claude/skills/deployment-patterns
$ npx degit Lukk17/agent-standards/.agents/skills/design-system .claude/skills/design-system
$ npx degit Lukk17/agent-standards/.agents/skills/docker-patterns .claude/skills/docker-patterns
$ npx degit Lukk17/agent-standards/.agents/skills/e2e-runbooks .claude/skills/e2e-runbooks
$ npx degit Lukk17/agent-standards/.agents/skills/e2e-testing .claude/skills/e2e-testing
$ npx degit Lukk17/agent-standards/.agents/skills/embedded-c-arduino .claude/skills/embedded-c-arduino
$ npx degit Lukk17/agent-standards/.agents/skills/frontend-design .claude/skills/frontend-design
$ npx degit Lukk17/agent-standards/.agents/skills/g-code-3d-printing .claude/skills/g-code-3d-printing
$ npx degit Lukk17/agent-standards/.agents/skills/git-workflow .claude/skills/git-workflow
$ npx degit Lukk17/agent-standards/.agents/skills/github-ops .claude/skills/github-ops
$ npx degit Lukk17/agent-standards/.agents/skills/golang-patterns .claude/skills/golang-patterns
$ npx degit Lukk17/agent-standards/.agents/skills/hexagonal-architecture .claude/skills/hexagonal-architecture
$ npx degit Lukk17/agent-standards/.agents/skills/home-assistant .claude/skills/home-assistant
$ npx degit Lukk17/agent-standards/.agents/skills/java-coding-standards .claude/skills/java-coding-standards
$ npx degit Lukk17/agent-standards/.agents/skills/jetbrains-ide-ops .claude/skills/jetbrains-ide-ops
$ npx degit Lukk17/agent-standards/.agents/skills/jira-integration .claude/skills/jira-integration
$ npx degit Lukk17/agent-standards/.agents/skills/keycloak-patterns .claude/skills/keycloak-patterns
$ npx degit Lukk17/agent-standards/.agents/skills/kicad .claude/skills/kicad
$ npx degit Lukk17/agent-standards/.agents/skills/markdown-writer .claude/skills/markdown-writer
$ npx degit Lukk17/agent-standards/.agents/skills/mongodb-patterns .claude/skills/mongodb-patterns
$ npx degit Lukk17/agent-standards/.agents/skills/nextjs-app-router-patterns .claude/skills/nextjs-app-router-patterns
$ npx degit Lukk17/agent-standards/.agents/skills/node-backend-patterns .claude/skills/node-backend-patterns
$ curl -fsSL --create-dirs -o .claude/agents/accessibility-expert.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/accessibility-expert.md
$ curl -fsSL --create-dirs -o .claude/agents/agent-engineer.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/agent-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/angular-expert.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/angular-expert.md
$ curl -fsSL --create-dirs -o .claude/agents/api-documenter.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/api-documenter.md
$ curl -fsSL --create-dirs -o .claude/agents/api-tester.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/api-tester.md
$ curl -fsSL --create-dirs -o .claude/agents/backend-architect.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/backend-architect.md
$ curl -fsSL --create-dirs -o .claude/agents/code-archaeologist.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/code-archaeologist.md
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/database-expert.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/database-expert.md
$ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/debugger.md
$ curl -fsSL --create-dirs -o .claude/agents/design-system-architect.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/design-system-architect.md
$ curl -fsSL --create-dirs -o .claude/agents/devops-automator.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/devops-automator.md
$ curl -fsSL --create-dirs -o .claude/agents/devops-troubleshooter.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/devops-troubleshooter.md
$ curl -fsSL --create-dirs -o .claude/agents/docs-architect.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/docs-architect.md
$ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/e2e-runner.md
$ curl -fsSL --create-dirs -o .claude/agents/embedded-c-engineer.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/embedded-c-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/error-detective.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/error-detective.md
$ curl -fsSL --create-dirs -o .claude/agents/flutter-expert.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/flutter-expert.md
$ curl -fsSL --create-dirs -o .claude/agents/go-pro.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/go-pro.md
$ curl -fsSL --create-dirs -o .claude/agents/home-assistant-engineer.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/home-assistant-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/java-pro.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/java-pro.md
$ curl -fsSL --create-dirs -o .claude/agents/legacy-modernizer.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/legacy-modernizer.md
$ curl -fsSL --create-dirs -o .claude/agents/legal-advisor.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/legal-advisor.md
$ curl -fsSL --create-dirs -o .claude/agents/ml-engineer.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/ml-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/observability-engineer.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/observability-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/performance-engineer.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/performance-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/project-manager.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/project-manager.md
$ curl -fsSL --create-dirs -o .claude/agents/python-pro.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/python-pro.md
$ curl -fsSL --create-dirs -o .claude/agents/react-nextjs-expert.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/react-nextjs-expert.md
$ curl -fsSL --create-dirs -o .claude/agents/release-manager.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/release-manager.md
$ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/security-auditor.md
$ curl -fsSL --create-dirs -o .claude/agents/seo-content-marketer.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/seo-content-marketer.md
$ curl -fsSL --create-dirs -o .claude/agents/test-automator.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/test-automator.md
$ curl -fsSL --create-dirs -o .claude/agents/ui-ux-designer.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/ui-ux-designer.md
$ curl -fsSL --create-dirs -o .claude/agents/unity-game-dev.md https://raw.githubusercontent.com/Lukk17/agent-standards/master/.claude/agents/unity-game-dev.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "^(Edit|Write|MultiEdit|NotebookEdit|Bash|PowerShell|WebFetch|WebSearch)$",
        "hooks": [
          {
            "type": "command",
            "command": "cd \"${CLAUDE_PROJECT_DIR}\" && PY=$(command -v python3 || command -v python) && \"$PY\" -S -E .agents/hooks/preflight_gate.py --format claude ; exit 0"
          }
        ]
      }
    ]
  }
}

MCP servers (8)

serversourceest. tokens
Context7 remote · remote 1.2k
MongoDB npm 6.0k
mcp-grafana · "grafana"
env: GRAFANA_SERVICE_ACCOUNT_TOKEN, GRAFANA_URL
pypi 2.5k
Playwright MCP · "playwright" npm 7.5k
Chrome DevTools MCP · "chrome-devtools" npm 9.0k
redis-mcp-server · "redis" pypi 2.5k
mcp/sonarqube · "sonarqube"
env: SONARQUBE_TOKEN, SONARQUBE_URL
docker 2.5k
n8n-mcp · "n8n"
env: N8N_API_KEY, N8N_API_URL
npm 2.5k

Skills (58)

Subagents (35)

accessibility-expert
model: inherit
Use when auditing for WCAG 2.1 / 2.2 compliance, remediating accessibility issues, or designing inclusive components. Tests with real assistive tech in mind (screen readers, keyboard-only, voice contr
agent-engineer
model: inherit
Use when the work is the AI agent configuration itself: writing or repairing a skill, a subagent definition, a preflight hook, an MCP server block, or an AGENTS.md file, and any research into how an a
angular-expert
model: inherit
Use when building or reviewing Angular code. Applies modern Angular (standalone components, signals, control flow, `inject()`), RxJS discipline, and OnPush change detection. Implementer, not architect
api-documenter
model: inherit
Use when writing or maintaining API documentation, whether OpenAPI 3.1, GraphQL SDL, AsyncAPI, or developer-portal prose. Produces docs a developer can ship against without asking a follow-up question
api-tester
model: inherit
Use when load-testing, contract-testing, or security-smoke-testing a running HTTP / GraphQL / gRPC API. Drives realistic traffic, validates responses against the spec, and finds the breaking point wit
backend-architect
model: opus
Use when designing a new backend service or revising an API contract, whether REST, GraphQL, gRPC, or event-driven. Produces an authoritative spec (OpenAPI or GraphQL schema) plus service boundaries,
code-archaeologist
model: inherit
Use when exploring an unfamiliar or legacy codebase before refactoring, onboarding, audit, or risk review. Maps architecture, surfaces hidden contracts and dead code, scores health, and produces a pri
code-reviewer
model: opus
Use PROACTIVELY after any code change before merging. Runs a severity-tagged review across correctness, security, performance, architecture, and tests. Read-only: produces a report with file:line cita
database-expert
model: opus
Use when designing a new data layer, choosing a database technology, modelling a schema, planning a migration, or tuning queries and indexes on an existing system. Two modes: design (greenfield or re-
debugger
model: opus
Use when an error, test failure, or unexpected behaviour needs root-cause analysis. Reproduces the failure, isolates the cause, applies the minimal fix, and verifies it. Returns a short diagnosis repo
design-system-architect
model: inherit
Use when establishing or evolving a design system, covering <redacted>, component library structure, multi-brand theming, or the design-to-code workflow. Produces the infrastructure the rest of the fr
devops-automator
model: inherit
Use when building or modifying CI/CD pipelines, Dockerfiles, Kubernetes manifests, infrastructure-as-code, or deployment workflows. Designs zero-downtime deployments with health checks and automated r
devops-troubleshooter
model: inherit
Use during a production incident in the infrastructure and runtime layer: crashing pods, DNS or networking faults, a deploy gone wrong, exhausted CPU, memory or disk. Gathers logs, metrics and traces,
docs-architect
model: inherit
Use when producing long-form technical documentation from a codebase: architecture manuals, system handbooks, onboarding guides, technical deep-dives. Reads the actual code and the git history, captur
e2e-runner
model: inherit
Use to execute ONE end-to-end capability test against a live stack and return its Verdict plus Result summary. Takes a single spec path and reports back independently, so a main session can fan a swee
embedded-c-engineer
model: inherit
Use when writing or reviewing embedded C / Arduino firmware, or designing the hardware around it (KiCad PCBs, 3D-printed enclosures and their G-code). Applies memory safety, non-blocking timing, ISR d
error-detective
model: inherit
Use when hunting application-level error patterns across logs and traces: one exception recurring across services, a spike that tracks a release, a data shape that walks a code path into a failure. Co
flutter-expert
model: inherit
Use when building or reviewing Flutter / Dart code for mobile, web, or desktop. Applies Dart 3 features (records, patterns, sealed classes), null safety, widget composition with const constructors, an
go-pro
model: inherit
Use when writing or reviewing Go service code, or when a Go package needs restructuring. Applies idiomatic Go (useful zero values, interfaces declared at the consumer, wrapped errors, context propagat
home-assistant-engineer
model: inherit
Use when building or reviewing Home Assistant configuration and automations. Applies strict YAML conventions, stable entity_id references, event-driven (not polling) automations, safe secret handling,
java-pro
model: inherit
Use when writing or reviewing Java / Spring Boot code, or when modernising a JVM service. Applies Java 21+ idioms (records, sealed types, pattern matching, virtual threads), Spring Boot 3 conventions,
legacy-modernizer
model: opus
Use when migrating frameworks, upgrading dependencies across breaking versions, decomposing a monolith, or paying down structural tech debt. Plans the migration in phases with tests added before each
legal-advisor
model: inherit
Use when drafting privacy policies, terms of service, cookie policies, data-processing agreements, or other compliance documentation. Produces drafts for a qualified attorney to review, never legal ad
ml-engineer
model: inherit
Use when writing or reviewing PyTorch training and inference code: model and dataset modules, the training loop, checkpointing, the evaluation harness, mixed precision and device placement, and packag
observability-engineer
model: inherit
Use when designing or extending production observability: logs, metrics, traces, SLOs, alerts, dashboards. Builds toward signals that drive action rather than vanity dashboards. Defers incident respon
performance-engineer
model: opus
Use when an application is slow, a deployment regressed performance, or you need a baseline before optimisation. Measures first, identifies the actual bottleneck with evidence, proposes the smallest c
project-manager
model: inherit
Use when work has to become tracked items: writing or splitting a ticket, turning a vague ask into testable acceptance criteria, triaging a backlog, or reconciling a Jira board and a GitHub milestone
python-pro
model: inherit
Use when writing or reviewing Python code, building FastAPI / Django / Flask services, or modernising a Python project. Applies 3.12+ idioms (type hints, dataclasses, structural pattern matching, asyn
react-nextjs-expert
model: inherit
Use when building or reviewing React 19 / Next.js 14+ code with the App Router. Applies Server Components by default, Client Components only where interactivity demands them, Server Actions for mutati
release-manager
model: inherit
Use when cutting a release: choosing the version, assembling release notes from the merged pull requests, checking the dependency and deployment gates, preparing the tag, and recording what actually s
security-auditor
model: opus
Use PROACTIVELY before any auth, payment, or sensitive-data change ships, and on demand for threat modelling, security architecture review, or vulnerability assessment. Covers threat modelling (STRIDE
seo-content-marketer
model: inherit
Use when planning content strategy, writing SEO content, optimising keyword usage, generating metadata, structuring content hierarchy, or auditing existing content for SEO and E-E-A-T. One agent cover
test-automator
model: inherit
Use PROACTIVELY after any code change to write the missing unit and integration tests in the codebase, run the relevant suites, analyse the failures, and fix them without weakening the test. Enforces
ui-ux-designer
model: inherit
Use when designing user flows, interface components, layouts, or running user research and usability validation. Two modes: UX research to understand the user, and interaction design to shape the flow
unity-game-dev
model: inherit
Use when building or reviewing Unity / C# game code. Applies frame-budget discipline (no per-frame allocations, cached component lookups), ScriptableObject-based architecture, the Unity Test Framework

Hooks (14)

eventmatcherruns
SessionStart*echo 'PREFLIGHT: before code work, name the skills and subagents that own this task and invoke them, or say none apply and why. Delegate investigation, review and bounded implementation by default. If the prompt asks anything, answer every
SessionStart*echo 'When you launch a background subagent, note how long its task should take and schedule a recurring check every 10 minutes while any subagent runs. At each check compare its running time and latest output with that expectation. Leave i
SessionStart*cd "${CLAUDE_PROJECT_DIR}" && PY=$(command -v python3 || command -v python) && "$PY" -S -E .agents/hooks/task_list_sync.py --event sessionstart --format claude ; exit 0
UserPromptSubmit*echo 'PREFLIGHT: before code work, name the skills and subagents that own this task and invoke them, or say none apply and why. Delegate investigation, review and bounded implementation by default. If the prompt asks anything, answer every
SubagentStart*echo '{"hookSpecificOutput": {"hookEventName": "SubagentStart", "additionalContext": "PREFLIGHT for a subagent: you are a subagent, and the main thread delegated this task to you. Do the work yourself with your own tools and load the skills
PreToolUse^(Edit|Write|MultiEdit|NotebookEdit|Bash|PowerShell|WebFetch|WebSearch)$cd "${CLAUDE_PROJECT_DIR}" && PY=$(command -v python3 || command -v python) && "$PY" -S -E .agents/hooks/preflight_gate.py --format claude ; exit 0
PostToolUse^(Edit|Write|MultiEdit)$cd "${CLAUDE_PROJECT_DIR}" && PY=$(command -v python3 || command -v python) && "$PY" -S -E .agents/hooks/markdown_lint_check.py --format claude ; exit 0
PreCompact*cd "${CLAUDE_PROJECT_DIR}" && PY=$(command -v python3 || command -v python) && "$PY" -S -E .agents/hooks/task_list_sync.py --event precompact --format claude ; exit 0
TaskCreated*cd "${CLAUDE_PROJECT_DIR}" && PY=$(command -v python3 || command -v python) && "$PY" -S -E .agents/hooks/task_list_sync.py --event taskcreated --format claude ; exit 0
TaskCompleted*cd "${CLAUDE_PROJECT_DIR}" && PY=$(command -v python3 || command -v python) && "$PY" -S -E .agents/hooks/task_list_sync.py --event taskcompleted --format claude ; exit 0
Stop*cd "${CLAUDE_PROJECT_DIR}" && PY=$(command -v python3 || command -v python) && "$PY" -S -E .agents/hooks/no_ai_markers_check.py --format claude --display-fixed ; exit 0
Stop*cd "${CLAUDE_PROJECT_DIR}" && PY=$(command -v python3 || command -v python) && "$PY" -S -E .agents/hooks/task_list_sync.py --event stop --format claude ; exit 0
SubagentStop*cd "${CLAUDE_PROJECT_DIR}" && PY=$(command -v python3 || command -v python) && "$PY" -S -E .agents/hooks/no_ai_markers_check.py --format claude ; exit 0
MessageDisplay*cd "${CLAUDE_PROJECT_DIR}" && PY=$(command -v python3 || command -v python) && "$PY" -S -E .agents/hooks/no_ai_markers_check.py --format claude --display ; exit 0

Similar rigs

copied ✓