watt-mind/factory
The factory that builds software — and itself. A runtime for self-improving agentic loops: the tracker is the control plane, git is the truth, CI is the gate.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/watt-mind/factory 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 watt-mind/factory/plugins/core/skills/factory-handoff .claude/skills/factory-handoff $ npx degit watt-mind/factory/plugins/core/skills/principle-attack-the-premise .claude/skills/principle-attack-the-premise $ npx degit watt-mind/factory/plugins/core/skills/principle-boundary-discipline .claude/skills/principle-boundary-discipline $ npx degit watt-mind/factory/plugins/core/skills/principle-build-the-lever .claude/skills/principle-build-the-lever $ npx degit watt-mind/factory/plugins/core/skills/principle-encode-lessons-in-structure .claude/skills/principle-encode-lessons-in-structure $ npx degit watt-mind/factory/plugins/core/skills/principle-exhaust-the-design-space .claude/skills/principle-exhaust-the-design-space $ npx degit watt-mind/factory/plugins/core/skills/principle-experience-first .claude/skills/principle-experience-first $ npx degit watt-mind/factory/plugins/core/skills/principle-explain-the-number .claude/skills/principle-explain-the-number $ npx degit watt-mind/factory/plugins/core/skills/principle-fix-root-causes .claude/skills/principle-fix-root-causes $ npx degit watt-mind/factory/plugins/core/skills/principle-foundational-thinking .claude/skills/principle-foundational-thinking $ npx degit watt-mind/factory/plugins/core/skills/principle-laziness-protocol .claude/skills/principle-laziness-protocol $ npx degit watt-mind/factory/plugins/core/skills/principle-make-operations-idempotent .claude/skills/principle-make-operations-idempotent $ npx degit watt-mind/factory/plugins/core/skills/principle-minimize-reader-load .claude/skills/principle-minimize-reader-load $ npx degit watt-mind/factory/plugins/core/skills/principle-model-the-domain .claude/skills/principle-model-the-domain $ npx degit watt-mind/factory/plugins/core/skills/principle-proceed-with-gates .claude/skills/principle-proceed-with-gates $ npx degit watt-mind/factory/plugins/core/skills/principle-redesign-from-first-principles .claude/skills/principle-redesign-from-first-principles $ npx degit watt-mind/factory/plugins/core/skills/principle-separate-before-serializing-shared-state .claude/skills/principle-separate-before-serializing-shared-state $ npx degit watt-mind/factory/plugins/core/skills/principle-subtract-before-you-add .claude/skills/principle-subtract-before-you-add $ npx degit watt-mind/factory/plugins/core/skills/principle-test-behavior-not-implementation .claude/skills/principle-test-behavior-not-implementation $ npx degit watt-mind/factory/plugins/core/skills/principle-type-system-discipline .claude/skills/principle-type-system-discipline $ npx degit watt-mind/factory/plugins/core/skills/principles .claude/skills/principles $ npx degit watt-mind/factory/plugins/core/skills/ticket-spec .claude/skills/ticket-spec
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 (22)
factory-handoffprinciple-attack-the-premiseprinciple-boundary-disciplineprinciple-build-the-leverprinciple-encode-lessons-in-structureprinciple-exhaust-the-design-spaceprinciple-experience-firstprinciple-explain-the-numberprinciple-fix-root-causesprinciple-foundational-thinkingprinciple-laziness-protocolprinciple-make-operations-idempotentprinciple-minimize-reader-loadprinciple-model-the-domainprinciple-proceed-with-gatesprinciple-redesign-from-first-principlesprinciple-separate-before-serializing-shared-stateprinciple-subtract-before-you-addprinciple-test-behavior-not-implementationprinciple-type-system-disciplineprinciplesticket-spec
Similar rigs
erickb336/sage
sage: a plugin for Claude Code (Codex support in progress) that turns a session into your chief of staff. A team of specialist agents designs, builds, reviews and proves the work; you answer product questions and look at results.
Skill Collector 5.2k tok · · Q0
erickb336/sage-stack
sage-stack: a multi-agent development stack for Claude Code and Codex. Your session becomes a chief of staff, and a team of agents designs, builds, reviews and tests each change, with the rules held in code. You answer product questions and
Skill Collector 5.2k tok · · Q0
paramcodes/skills
Personal agent skills + a curated catalogue of community collections (Matt Pocock, gstack, Emil Kowalski, pstack, impeccable, ui-ux-pro-max, caveman, vercel). npx skills add paramcodes/skills
Skill Collector 2.3k tok · · Q0
rnegron/dotfiles
A repository for hosting my MacOS configuration files
Skill Collector 3.1k tok · · Q5