nbfrodri/agent-tack
My AI coding setup in one repo, for Claude Code, Codex, Gemini, Copilot, OpenCode, Crush and Cursor: instructions, skills, agents, sets you activate per project, safety hooks and a command guard, risk-based workflow modes and checks chosen
field: Developer tools workflow: Testing & TDDFrontend & designGit & commitsDocsPR / code review runs claude in CI
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit nbfrodri/agent-tack/agents ./rig-agent-tack/agents $ npx degit nbfrodri/agent-tack/skills ./rig-agent-tack/skills $ npx degit nbfrodri/agent-tack/hooks ./rig-agent-tack/hooks
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.
$ npx degit nbfrodri/agent-tack/skills/api-design .claude/skills/api-design $ npx degit nbfrodri/agent-tack/skills/auth .claude/skills/auth $ npx degit nbfrodri/agent-tack/skills/auto-improve .claude/skills/auto-improve $ npx degit nbfrodri/agent-tack/skills/cross-delegate .claude/skills/cross-delegate $ npx degit nbfrodri/agent-tack/skills/database .claude/skills/database $ npx degit nbfrodri/agent-tack/skills/debugging .claude/skills/debugging $ npx degit nbfrodri/agent-tack/skills/deployment .claude/skills/deployment $ npx degit nbfrodri/agent-tack/skills/dev-workflow .claude/skills/dev-workflow $ npx degit nbfrodri/agent-tack/skills/e2e-testing .claude/skills/e2e-testing $ npx degit nbfrodri/agent-tack/skills/frontend .claude/skills/frontend $ npx degit nbfrodri/agent-tack/skills/git-history .claude/skills/git-history $ npx degit nbfrodri/agent-tack/skills/github-issues .claude/skills/github-issues $ npx degit nbfrodri/agent-tack/skills/improve .claude/skills/improve $ npx degit nbfrodri/agent-tack/skills/lessons .claude/skills/lessons $ npx degit nbfrodri/agent-tack/skills/libraries .claude/skills/libraries $ npx degit nbfrodri/agent-tack/skills/new-project .claude/skills/new-project $ npx degit nbfrodri/agent-tack/skills/observability .claude/skills/observability $ npx degit nbfrodri/agent-tack/skills/orchestrate .claude/skills/orchestrate $ npx degit nbfrodri/agent-tack/skills/project-docs .claude/skills/project-docs $ npx degit nbfrodri/agent-tack/skills/release .claude/skills/release $ npx degit nbfrodri/agent-tack/skills/showcase-ui .claude/skills/showcase-ui $ npx degit nbfrodri/agent-tack/skills/tack .claude/skills/tack $ npx degit nbfrodri/agent-tack/skills/testing .claude/skills/testing $ npx degit nbfrodri/agent-tack/skills/ui-references .claude/skills/ui-references
$ curl -fsSL --create-dirs -o .claude/agents/architecture-reviewer.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/architecture-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/critic.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/critic.md $ curl -fsSL --create-dirs -o .claude/agents/docs-writer.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/docs-writer.md $ curl -fsSL --create-dirs -o .claude/agents/evaluator.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/evaluator.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/performance-analyzer.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/performance-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/security-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/test-writer.md $ curl -fsSL --create-dirs -o .claude/agents/ui-reviewer.md https://raw.githubusercontent.com/nbfrodri/agent-tack/main/agents/ui-reviewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (24)
api-designauthauto-improvecross-delegatedatabasedebuggingdeploymentdev-workflowe2e-testingfrontendgit-historygithub-issuesimprovelessonslibrariesnew-projectobservabilityorchestrateproject-docsreleaseshowcase-uitacktestingui-references
Subagents (11)
| architecture-reviewer model: inherit | Read-only architecture review of existing code, covering layering, dependency direction, coupling, DDD boundaries and debt hot spots, with prioritised evidence-backed proposals. Used by improve or on |
| code-reviewer model: inherit | Reviews a diff, branch or PR (or a whole scope in project mode) for bugs, tests, design, security, conventions and docs. Use after implementing and before pushing or opening a PR. |
| critic model: inherit | Read-only adversarial critic of a proposal, plan or design before code is written. Finds hidden assumptions, failure modes and over-engineering, suggests a simpler option and asks the user questions. |
| docs-writer model: haiku | Keeps README, AGENTS.md, docs/, .env.example and CHANGELOG in sync with the code, writes ADRs and logs AI work. Use at the end of a task that changed behaviour, config, APIs or architecture. |
| evaluator model: inherit | Read-only scorer for requested assessments that rates applicable dimensions with a stated rubric and evidence, explains changes from earlier results, and identifies concrete issues. Scores are not pro |
| implementer model: inherit | Implements one planned task end to end on its own branch or worktree, following the user's workflow, and reports back. Used by orchestrate. |
| performance-analyzer model: inherit | Measures and ranks performance problems across the stack (Web Vitals, bundle, API latency, DB queries, caching) before recommending fixes. Use when something is slow or needs optimising. |
| planner model: inherit | Read-only architect that turns a request into an implementation plan with acceptance criteria, design, tests first, commit breakdown, docs, issue breakdown. Use for non-trivial features, refactors or |
| security-auditor model: inherit | Read-only security audit of code, config and infrastructure, covering OWASP Top 10, auth, injection, secrets, dependencies, CI. Use before releases, after auth/payment/upload changes, or on request. |
| test-writer model: inherit | Adds tests to existing code (coverage gaps, characterisation tests before refactors) without touching production code; report-only mode for assessments. Not for new features under TDD. |
| ui-reviewer model: inherit | Reviews a running web app at mobile and desktop widths (hierarchy, consistency, states, forms, accessibility), or compares tack shots before and after screenshots for concrete regressions. Used by imp |
Similar rigs
Yassinekrn/claude-setup
Personal Claude Code setup — orchestrator/subagent delegation policy, custom agents, and a colored PowerShell statusline (git branch, model+effort, tokens, cost, rate limits).
Orchestrator 1.2k tok · · Q15
yassine-krichen/claude-code-agentic-setup
Personal Claude Code setup — orchestrator/subagent delegation policy, custom agents, and a colored PowerShell statusline (git branch, model+effort, tokens, cost, rate limits).
Orchestrator 2.3k tok · · Q23
kapadias/nonna
Your AI agent says done. Nonna makes it prove it: she runs your test suite before a coding agent can stop, and blocks pushes to main and secrets in files. Claude Code plugin, plus git hooks for Codex, Cursor, Copilot, Gemini and more
Fort Knox 3.9k tok · · Q78
ingenierodeatascos-cyber/ai-project-template
AI-First project template for building software with orchestrated AI agents using Spec-Driven Development. Includes router, planner, implementer and reviewer workflows for structured development with Codex, Claude Code or similar AI coding
Orchestrator 196 tok · · Q0