MiselKING/agents-review
Learning project in agent-driven development. The human sets the rules, gives rough issue notes, approves plans, does final review and merges; AI agents draft the full issue, plan, implement, test and do first-pass PR review. The app: a sma
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · No YOLO mode · Sandbox or ask-first rules · details
Quality 26/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit MiselKING/agents-review/.claude ./rig-agents-review # 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.
$ npx degit MiselKING/agents-review/.claude/skills/add-graphql-field .claude/skills/add-graphql-field $ npx degit MiselKING/agents-review/.claude/skills/write-issue .claude/skills/write-issue $ npx degit MiselKING/agents-review/.claude/skills/write-tests .claude/skills/write-tests
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Read(**/.env)",
"Read(**/.env.local)",
"Read(**/.env.*.local)",
"Read(**/.env.dev)",
"Read(**/.env.development)",
"Read(**/.env.prod)",
"Read(**/.env.production)",
"Read(**/.env.staging)",
"Read(**/.env.test)",
"Read(./docs/private/**)",
"Edit(./docs/private/**)",
"Edit(./apps/api/src/generated/**)",
"Edit(./apps/web/src/gql/**)",
"Edit(./packages/db/drizzle/**)",
"Bash(git push --force*)",
"Bash(git push * --force*)",
"Bash(git push -f*)",
"Bash(git push * -f*)",
"Bash(git push *+*)",
"Bash(git push * main)",
"Bash(git push *:main)",
"Bash(gh pr merge *)",
"Bash(gh pr review *)",
"Bash(npm *)",
"Bash(npx *)",
"Bash(yarn *)",
"Bash(*drizzle-kit push*)"
],
"ask": [
"Edit(./docs/_project-plan.md)",
"Read(./docs/AGENTS.md.example)",
"Edit(**/AGENTS.md)",
"Edit(**/CLAUDE.md)",
"Edit(./REVIEW.md)",
"Edit(./.claude/**)",
"Edit(./.github/**)",
"Edit(./.devcontainer/**)",
"Edit(./pnpm-workspace.yaml)",
"Edit(./packages/db/src/schema.ts)",
"Bash(pnpm add *)",
"Bash(pnpm * add *)",
"Bash(pnpm update *)",
"Bash(pnpm * update *)",
"Bash(pnpm up *)",
"Bash(pnpm remove *)",
"Bash(pnpm * remove *)"
]
}
} Skills (3)
Hooks (2)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Edit|Write | node "${CLAUDE_PROJECT_DIR}/.claude/hooks/lint-edited-file.ts" |
| Stop | * | node "${CLAUDE_PROJECT_DIR}/.claude/hooks/check-before-stop.ts" |
Permissions
deny (27)
Read(**/.env)
Read(**/.env.local)
Read(**/.env.*.local)
Read(**/.env.dev)
Read(**/.env.development)
Read(**/.env.prod)
Read(**/.env.production)
Read(**/.env.staging)
Read(**/.env.test)
Read(./docs/private/**)
Edit(./docs/private/**)
Edit(./apps/api/src/generated/**)
Edit(./apps/web/src/gql/**)
Edit(./packages/db/drizzle/**)
Bash(git push --force*)
Bash(git push * --force*)
Bash(git push -f*)
Bash(git push * -f*)
Bash(git push *+*)
Bash(git push * main)
Bash(git push *:main)
Bash(gh pr merge *)
Bash(gh pr review *)
Bash(npm *)
Bash(npx *)
Bash(yarn *)
Bash(*drizzle-kit push*)
ask (17)
Edit(./docs/_project-plan.md)
Read(./docs/AGENTS.md.example)
Edit(**/AGENTS.md)
Edit(**/CLAUDE.md)
Edit(./REVIEW.md)
Edit(./.claude/**)
Edit(./.github/**)
Edit(./.devcontainer/**)
Edit(./pnpm-workspace.yaml)
Edit(./packages/db/src/schema.ts)
Bash(pnpm add *)
Bash(pnpm * add *)
Bash(pnpm update *)
Bash(pnpm * update *)
Bash(pnpm up *)
Bash(pnpm remove *)
Bash(pnpm * remove *)
allow (10)
Bash(pnpm lint)
Bash(pnpm typecheck)
Bash(pnpm test)
Bash(pnpm test:e2e)
Bash(pnpm test:hooks)
Bash(pnpm format)
Bash(pnpm format:check)
Bash(pnpm codegen)
Bash(pnpm codegen:check)
Bash(pnpm --filter * exec vitest run *)
Similar rigs
Anyesh/skillprobe
Automated end-to-end testing for AI agent skills(agentskills.io). Launches Claude Code and Cursor as subprocesses, runs scenarios in real workspaces, and asserts what the model actually does.
Minimalist 54 tok · · Q0
karawanshy/kiro2claude
Use .kiro/ agents, skills, steering, specs and hooks directly from Claude Code — one source of truth, no duplicated AI config.
Pragmatist 567 tok · · Q0
Fafnur/fafnur
Aleksandr Serenko — Frontend Team Lead. Source of fafn.ru: Angular 22 SSG, Nx, Tailwind CSS, Vitest, Playwright, AI-driven workflow with Claude Code.
Pragmatist 1.4k tok · · Q0
reyxdz/going-dark
One strict way to run a software project with any AI coding agent: issues as specs, handoff prompts, audits that catch every problem down to a typo, and fixes for what they find.
Pragmatist 1.0k tok · · Q0