vannt-dev/governed-agent-sdlc
Ship with agents. Keep humans in control. Cross-platform governance toolkit for AI coding agents.
stack: Python
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details
Quality 24/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit vannt-dev/governed-agent-sdlc/.claude ./rig-governed-agent-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.
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/vannt-dev/governed-agent-sdlc/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/vannt-dev/governed-agent-sdlc/main/.claude/agents/developer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/vannt-dev/governed-agent-sdlc/main/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/publisher.md https://raw.githubusercontent.com/vannt-dev/governed-agent-sdlc/main/.claude/agents/publisher.md $ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/vannt-dev/governed-agent-sdlc/main/.claude/agents/qa.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/vannt-dev/governed-agent-sdlc/main/.claude/agents/reviewer.md
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.*)",
"Read(**/*credential*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash|PowerShell|Read|Glob|Grep",
"hooks": [
{
"type": "command",
"command": "uv run --no-project python hooks/guard_credentials.py"
}
]
},
{
"matcher": "Bash|PowerShell",
"hooks": [
{
"type": "command",
"command": "uv run --no-project python hooks/guard_git.py"
}
]
},
{
"matcher": "Write|Edit|MultiEdit",
"hooks": [
{
"type": "command",
"command": "uv run --no-project python hooks/guard_role_scope.py"
}
]
},
{
"matcher": "Agent|Task",
"hooks": [
{
"type": "command",
"command": "uv run --no-project python hooks/guard_role_gate.py"
}
]
}
]
}
} Subagents (6)
| architect model: opus | Governed architect role generated by Governed Agent SDLC. Invoke explicitly. |
| developer model: sonnet | Governed developer role generated by Governed Agent SDLC. Invoke explicitly. |
| planner model: opus | Governed planner role generated by Governed Agent SDLC. Invoke explicitly. |
| publisher model: haiku | Governed publisher role generated by Governed Agent SDLC. Invoke explicitly. |
| qa model: sonnet | Governed qa role generated by Governed Agent SDLC. Invoke explicitly. |
| reviewer model: opus | Governed reviewer role generated by Governed Agent SDLC. Invoke explicitly. |
Hooks (4)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash|PowerShell|Read|Glob|Grep | uv run --no-project python hooks/guard_credentials.py |
| PreToolUse | Bash|PowerShell | uv run --no-project python hooks/guard_git.py |
| PreToolUse | Write|Edit|MultiEdit | uv run --no-project python hooks/guard_role_scope.py |
| PreToolUse | Agent|Task | uv run --no-project python hooks/guard_role_gate.py |
Permissions
deny (3)
Read(**/.env)
Read(**/.env.*)
Read(**/*credential*)
ask (0)
—
allow (0)
—
Similar rigs
eugeek/claude-config-tdd
Claude Code config with TDD workflow, plan -> tests -> red -> implementation -> green -> review -> shipment
Orchestrator 5.8k tok · · Q29
xhulz/nina
Harness orchestration for Claude Code: composes a gated multi-agent pipeline into projects from versioned layers, holds its loop caps with hooks, measures it from transcripts, and turns recurring mistakes into rules.
Orchestrator 12.0k tok · · Q25
yeyo11/agentry
Run Claude Code as a service: REST API, web UI and multi-agent orchestration in one container
Pragmatist 5.2k tok · · Q18
IntuitivePhella/AI-PhellOS
Portable AI development workflow template and CLI for spec-driven, test-aware software delivery with Codex, Claude Code, and other coding agents.
Orchestrator 3.1k tok · · Q31