KaaS-team/KaaS-factory
Open-source software factory: turns tracker issues into reviewed, gated pull requests with the coding agents, trackers and CI you already use. Built by KaaS, kaas.team
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 51/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit KaaS-team/KaaS-factory/.claude ./rig-kaas-factory # 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 KaaS-team/KaaS-factory/.claude/skills/factory-build .claude/skills/factory-build $ npx degit KaaS-team/KaaS-factory/.claude/skills/factory-comment .claude/skills/factory-comment $ npx degit KaaS-team/KaaS-factory/.claude/skills/factory-operator .claude/skills/factory-operator $ npx degit KaaS-team/KaaS-factory/.claude/skills/factory-plan .claude/skills/factory-plan $ npx degit KaaS-team/KaaS-factory/.claude/skills/factory-pr .claude/skills/factory-pr $ npx degit KaaS-team/KaaS-factory/.claude/skills/factory-retro .claude/skills/factory-retro $ npx degit KaaS-team/KaaS-factory/.claude/skills/factory-triage .claude/skills/factory-triage $ npx degit KaaS-team/KaaS-factory/.claude/skills/factory-verify .claude/skills/factory-verify $ npx degit KaaS-team/KaaS-factory/template/.claude/skills/factory-architecture .claude/skills/factory-architecture $ npx degit KaaS-team/KaaS-factory/template/.claude/skills/factory-plan-rubric .claude/skills/factory-plan-rubric
$ curl -fsSL --create-dirs -o .claude/agents/factory-plan-critic.md https://raw.githubusercontent.com/KaaS-team/KaaS-factory/main/.claude/agents/factory-plan-critic.md $ curl -fsSL --create-dirs -o .claude/agents/factory-reviewer.md https://raw.githubusercontent.com/KaaS-team/KaaS-factory/main/.claude/agents/factory-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/factory-plan-critic.md https://raw.githubusercontent.com/KaaS-team/KaaS-factory/main/template/.claude/agents/factory-plan-critic.md $ curl -fsSL --create-dirs -o .claude/agents/factory-reviewer.md https://raw.githubusercontent.com/KaaS-team/KaaS-factory/main/template/.claude/agents/factory-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*)",
"Bash(make agent-matrix)",
"Bash(bun scripts/agent-matrix.ts)",
"Bash(bun scripts/agent-matrix.ts *)",
"Bash(git push --force *)",
"Bash(git push -f *)",
"Bash(git push * --force*)",
"Bash(git push * -f*)",
"Bash(git push * +*)",
"Bash(git push --force-with-lease*)",
"Bash(gh *)",
"Bash(git push*)",
"Bash(git merge *)",
"Bash(git reset --hard *)",
"Bash(git push --force*)",
"Bash(git push -f*)",
"Read(~/.config/gh/**)",
"Read(~/.ssh/**)",
"Read(./.env*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Edit|Write|MultiEdit|NotebookEdit|Read|Bash|Agent|Grep|Glob",
"hooks": [
{
"type": "command",
"command": ".claude/hooks/guard-paths.sh"
}
]
}
]
}
} Skills (10)
factory-buildfactory-commentfactory-operatorfactory-planfactory-prfactory-retrofactory-triagefactory-verifyfactory-architecturefactory-plan-rubric
Subagents (4)
| factory-plan-critic model: sonnet | Use this agent once during factory-plan, after the plan comment is drafted and before it is final, to check the draft against a fixed three-item checklist. It returns must-fix items only; it does not |
| factory-reviewer model: sonnet | Use this agent during factory-verify, in a fresh read-only context, to review a build's diff for correctness, security (injection, authz, secrets), and non-goal violations that a passing test suite wo |
| factory-plan-critic model: sonnet | Use this agent once during factory-plan, after the plan comment is drafted and before it is final, to check the draft against a fixed three-item checklist. It returns must-fix items only; it does not |
| factory-reviewer model: sonnet | Use this agent during factory-verify, in a fresh read-only context, to review a build's diff for correctness, security (injection, authz, secrets), and non-goal violations that a passing test suite wo |
Hooks (5)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | cd "$CLAUDE_PROJECT_DIR" && bun scripts/goals.ts --next |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit|Read|Bash|Agent|Grep|Glob | .claude/hooks/guard-paths.sh |
| Stop | * | .claude/hooks/stop-artifact.sh |
| Stop | * | .claude/hooks/stop-verifier-evidence.sh |
| PostToolUse | Edit|Write|MultiEdit | .claude/hooks/post-edit-check.sh |
Permissions
deny (19)
Read(./.env*)
Bash(make agent-matrix)
Bash(bun scripts/agent-matrix.ts)
Bash(bun scripts/agent-matrix.ts *)
Bash(git push --force *)
Bash(git push -f *)
Bash(git push * --force*)
Bash(git push * -f*)
Bash(git push * +*)
Bash(git push --force-with-lease*)
Bash(gh *)
Bash(git push*)
Bash(git merge *)
Bash(git reset --hard *)
Bash(git push --force*)
Bash(git push -f*)
Read(~/.config/gh/**)
Read(~/.ssh/**)
Read(./.env*)
ask (0)
—
allow (7)
Bash(make check)
Bash(make typecheck)
Bash(make test)
Bash(make skills-check)
Bash(bun test)
Bash(bun x tsc --noEmit)
Bash(git status *)
Similar rigs
adamwardecki/job-tracker-mcp
A disciplined job search plugin for Claude Code and Hermes Agent
Skill Collector 6.1k tok · · Q18
domain-centric-development/dca-marketplace
A Claude Code plugin marketplace that packages Domain-Driven Design, Hexagonal Architecture, and Clean Architecture as ready-to-use skills and agents.
Skill Collector 7.3k tok · · Q5
ruvnet/RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
Fort Knox 14.1k tok · · Q20
ruvnet/ruflo
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native
Fort Knox 35.3k tok · · Q49