martinisef/ai_sdlc
The AI-native SDLC loop in your repo: agents write intent, spec, plan and code; people approve each gate in git; guardrails for Claude Code, Cursor and AGENTS.md agents.
field: Developer tools workflow: Planning & specsPR / code reviewTesting & TDDGit & commitsDocs 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 martinisef/ai_sdlc/examples/python-api/.claude ./rig-ai_sdlc # 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 martinisef/ai_sdlc/content/en/skills/policy-secure-api .claude/skills/policy-secure-api $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-build .claude/skills/sdlc-build $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-explain .claude/skills/sdlc-explain $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-fix .claude/skills/sdlc-fix $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-incident .claude/skills/sdlc-incident $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-intent .claude/skills/sdlc-intent $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-plan .claude/skills/sdlc-plan $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-quick .claude/skills/sdlc-quick $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-roadmap .claude/skills/sdlc-roadmap $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-setup .claude/skills/sdlc-setup $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-ship .claude/skills/sdlc-ship $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-spec .claude/skills/sdlc-spec $ npx degit martinisef/ai_sdlc/content/en/skills/sdlc-status .claude/skills/sdlc-status
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/martinisef/ai_sdlc/main/examples/python-api/.claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/simplifier.md https://raw.githubusercontent.com/martinisef/ai_sdlc/main/examples/python-api/.claude/agents/simplifier.md $ curl -fsSL --create-dirs -o .claude/agents/spec-reviewer.md https://raw.githubusercontent.com/martinisef/ai_sdlc/main/examples/python-api/.claude/agents/spec-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/martinisef/ai_sdlc/main/examples/python-api/.claude/agents/verifier.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/martinisef/ai_sdlc/main/examples/typescript-lib/.claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/simplifier.md https://raw.githubusercontent.com/martinisef/ai_sdlc/main/examples/typescript-lib/.claude/agents/simplifier.md $ curl -fsSL --create-dirs -o .claude/agents/spec-reviewer.md https://raw.githubusercontent.com/martinisef/ai_sdlc/main/examples/typescript-lib/.claude/agents/spec-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/martinisef/ai_sdlc/main/examples/typescript-lib/.claude/agents/verifier.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",
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.sdlc/bin/sdlc hook pre-tool --agent claude"
},
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.sdlc/bin/sdlc hook pre-tool --agent claude"
}
]
}
]
}
} Skills (13)
policy-secure-apisdlc-buildsdlc-explainsdlc-fixsdlc-incidentsdlc-intentsdlc-plansdlc-quicksdlc-roadmapsdlc-setupsdlc-shipsdlc-specsdlc-status
Subagents (8)
| researcher | Explores the codebase to answer a concrete question (where X lives, how Y works, what can be reused for Z) and returns a summary with paths, without filling up the main session's context. Use in /sdlc |
| simplifier | Reviews the current branch's diff and removes unnecessary complexity (premature abstractions, dead code, duplication, redundant error handling) without changing behavior. Use after the main implementa |
| spec-reviewer | Adversarial review of a spec.md against its intent.md. Looks for unverifiable requirements, unsolved parts of the problem, lost open questions, unapplied policies and missing concerns. Use in /sdlc-sp |
| verifier | Runs the app and verifies that the change works before the session considers it done. Compares the behavior against changes/<slug>/plan.md. Use at the end of /sdlc-build or when asked to verify a chan |
| researcher | Explores the codebase to answer a concrete question (where X lives, how Y works, what can be reused for Z) and returns a summary with paths, without filling up the main session's context. Use in /sdlc |
| simplifier | Reviews the current branch's diff and removes unnecessary complexity (premature abstractions, dead code, duplication, redundant error handling) without changing behavior. Use after the main implementa |
| spec-reviewer | Adversarial review of a spec.md against its intent.md. Looks for unverifiable requirements, unsolved parts of the problem, lost open questions, unapplied policies and missing concerns. Use in /sdlc-sp |
| verifier | Runs the app and verifies that the change works before the session considers it done. Compares the behavior against changes/<slug>/plan.md. Use at the end of /sdlc-build or when asked to verify a chan |
Hooks (8)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | "$CLAUDE_PROJECT_DIR"/.sdlc/bin/sdlc hook session-start --agent claude |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit|Bash | "$CLAUDE_PROJECT_DIR"/.sdlc/bin/sdlc hook pre-tool --agent claude |
| PostToolUse | Edit|Write|MultiEdit | "$CLAUDE_PROJECT_DIR"/.sdlc/bin/sdlc hook post-tool --agent claude |
| Stop | * | "$CLAUDE_PROJECT_DIR"/.sdlc/bin/sdlc hook stop --agent claude |
| SessionStart | * | "$CLAUDE_PROJECT_DIR"/.sdlc/bin/sdlc hook session-start --agent claude |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit|Bash | "$CLAUDE_PROJECT_DIR"/.sdlc/bin/sdlc hook pre-tool --agent claude |
| PostToolUse | Edit|Write|MultiEdit | "$CLAUDE_PROJECT_DIR"/.sdlc/bin/sdlc hook post-tool --agent claude |
| Stop | * | "$CLAUDE_PROJECT_DIR"/.sdlc/bin/sdlc hook stop --agent claude |
Cursor rules (2)
ai-sdlc · alwaysai-sdlc · always
Similar rigs
datenwissenschaften/retro-speedlab
Cookiecutter template for Retro Speedlab game packages: a skeleton that scheduled Claude Code lab runs grow until the TAS search beats the game.
YOLO Cowboy 353 tok · · Q6
iuliandita/agents
Global prompts and subagent roles for coding agents, deployed to every harness you use.
Orchestrator 1.5k tok · · Q3
Remus3/Resin-Compute
Genshin Impact wish and pity forecaster on an absorbing Markov chain, with resin budgeting, goal planning and an Enka.Network profile client. Headless-first Python 3.11, stdlib-only at runtime, no game data vendored.
Orchestrator 11.3k tok · · Q51
Remus3/ClockSpeed
Local, deterministic production planner and advisor for Satisfactory. Reads your own game install and save file instead of a wiki dump, so answers match the patch you are actually playing. Exact rational arithmetic, no language model in the
Orchestrator 10.6k tok · · Q51