umararshad4/honey-stack
Always-on workflow layer for Claude Code and Codex: right-sized tasks, smallest complete change, proof before done, plus RSI that learns from every session.
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit umararshad4/honey-stack/skills ./rig-honey-stack/skills 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 umararshad4/honey-stack/skills/api-design .claude/skills/api-design $ npx degit umararshad4/honey-stack/skills/architecture .claude/skills/architecture $ npx degit umararshad4/honey-stack/skills/database .claude/skills/database $ npx degit umararshad4/honey-stack/skills/debug .claude/skills/debug $ npx degit umararshad4/honey-stack/skills/deploy .claude/skills/deploy $ npx degit umararshad4/honey-stack/skills/docs .claude/skills/docs $ npx degit umararshad4/honey-stack/skills/domain .claude/skills/domain $ npx degit umararshad4/honey-stack/skills/execute .claude/skills/execute $ npx degit umararshad4/honey-stack/skills/frontend .claude/skills/frontend $ npx degit umararshad4/honey-stack/skills/gain .claude/skills/gain $ npx degit umararshad4/honey-stack/skills/grill .claude/skills/grill $ npx degit umararshad4/honey-stack/skills/handoff .claude/skills/handoff $ npx degit umararshad4/honey-stack/skills/honey .claude/skills/honey $ npx degit umararshad4/honey-stack/skills/incident .claude/skills/incident $ npx degit umararshad4/honey-stack/skills/observability .claude/skills/observability $ npx degit umararshad4/honey-stack/skills/opensrc .claude/skills/opensrc $ npx degit umararshad4/honey-stack/skills/perf .claude/skills/perf $ npx degit umararshad4/honey-stack/skills/plan .claude/skills/plan $ npx degit umararshad4/honey-stack/skills/principles .claude/skills/principles $ npx degit umararshad4/honey-stack/skills/project-verify .claude/skills/project-verify $ npx degit umararshad4/honey-stack/skills/prototype .claude/skills/prototype $ npx degit umararshad4/honey-stack/skills/qa .claude/skills/qa $ npx degit umararshad4/honey-stack/skills/research .claude/skills/research $ npx degit umararshad4/honey-stack/skills/reverse-engineer .claude/skills/reverse-engineer $ npx degit umararshad4/honey-stack/skills/review .claude/skills/review $ npx degit umararshad4/honey-stack/skills/rsi .claude/skills/rsi $ npx degit umararshad4/honey-stack/skills/security .claude/skills/security $ npx degit umararshad4/honey-stack/skills/ship .claude/skills/ship $ npx degit umararshad4/honey-stack/skills/stageshow .claude/skills/stageshow $ npx degit umararshad4/honey-stack/skills/statechart .claude/skills/statechart $ npx degit umararshad4/honey-stack/skills/tdd .claude/skills/tdd $ npx degit umararshad4/honey-stack/skills/teach .claude/skills/teach $ npx degit umararshad4/honey-stack/skills/test-design .claude/skills/test-design $ npx degit umararshad4/honey-stack/skills/tooling .claude/skills/tooling $ npx degit umararshad4/honey-stack/skills/triage .claude/skills/triage $ npx degit umararshad4/honey-stack/skills/unslop .claude/skills/unslop $ npx degit umararshad4/honey-stack/skills/upgrade .claude/skills/upgrade $ npx degit umararshad4/honey-stack/skills/verify .claude/skills/verify $ npx degit umararshad4/honey-stack/skills/write-skill .claude/skills/write-skill
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 (39)
Similar rigs
dayfinggg/openai-codex-agent-skills
Current Codex instructions, 22 engineering skills, and portable settings with Windows and Linux installers.
Skill Collector 2.0k tok · · Q0
iamvonpasion/hashb
Dev workflow toolkit for Claude Code — 14 skills that turn AI into a structured development partner. Spec → Design → Eng → TDD → Review → QA → Ship.
Skill Collector 2.5k tok · · Q0
chengxuniucode/ForgeTeam
AI coding framework — one person, full team delivery. Pure Shell+Markdown, zero dependencies, works with Claude Code / Cursor / Codex / OpenCode. 开源 AI 编码框架,一人全栈交付。
Skill Collector 748 tok · · Q23
ksprashu/agent-skill-forge
Curated, unified monorepo of high-performance skills for Google Antigravity, Claude Code, Gemini CLI, and agentic AI coding assistants.
Skill Collector 2.7k tok · · Q20