AiJasu/claude-code-harness
Claude Code config: global instructions, hooks that enforce them (with tests), skills, output style
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 AiJasu/claude-code-harness/agents ./rig-claude-code-harness/agents $ npx degit AiJasu/claude-code-harness/skills ./rig-claude-code-harness/skills $ npx degit AiJasu/claude-code-harness/hooks ./rig-claude-code-harness/hooks
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 AiJasu/claude-code-harness/skills/best .claude/skills/best $ npx degit AiJasu/claude-code-harness/skills/careful .claude/skills/careful $ npx degit AiJasu/claude-code-harness/skills/commit .claude/skills/commit $ npx degit AiJasu/claude-code-harness/skills/critic-loop .claude/skills/critic-loop $ npx degit AiJasu/claude-code-harness/skills/debug .claude/skills/debug $ npx degit AiJasu/claude-code-harness/skills/drive-screen .claude/skills/drive-screen $ npx degit AiJasu/claude-code-harness/skills/execute .claude/skills/execute $ npx degit AiJasu/claude-code-harness/skills/freeze .claude/skills/freeze $ npx degit AiJasu/claude-code-harness/skills/guard-off .claude/skills/guard-off $ npx degit AiJasu/claude-code-harness/skills/handoff .claude/skills/handoff $ npx degit AiJasu/claude-code-harness/skills/plan .claude/skills/plan $ npx degit AiJasu/claude-code-harness/skills/prime .claude/skills/prime $ npx degit AiJasu/claude-code-harness/skills/security-scan .claude/skills/security-scan $ npx degit AiJasu/claude-code-harness/skills/spec .claude/skills/spec $ npx degit AiJasu/claude-code-harness/skills/wrap .claude/skills/wrap
$ curl -fsSL --create-dirs -o .claude/agents/lean-worker.md https://raw.githubusercontent.com/AiJasu/claude-code-harness/main/agents/lean-worker.md 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 (15)
bestcarefulcommitcritic-loopdebugdrive-screenexecutefreezeguard-offhandoffplanprimesecurity-scanspecwrap
Subagents (1)
| lean-worker | Mechanical or transcription workflow stage that works from a finished spec or explicit instructions (rote edits, format conversion, listings, file assembly). Not for orchestrators, critics, judges or |
Similar rigs
lutzleonhardt/casefile
AI-assisted development that git blame can explain — preserve the decisions behind every change.
Pragmatist 190 tok · · Q0
nicodiansk/turbocharge
Opinionated engineering pipeline for Claude Code: 10 skills, 6 agents, 2 hooks, 1 workflow. Replaces ad-hoc agent sprawl with brainstorm → story → plan → build → review → ship.
Pragmatist 5.4k tok · · Q5
nicodiansk/turboflow
Opinionated engineering pipeline for Claude Code with 10 skills, 5 agents, 2 hooks. Replaces ad-hoc agent sprawl with brainstorm → story → plan → build → review → ship.
Pragmatist 2.1k tok · · Q0
hta218/dotfiles
My personal macOS development environment — shell config, Git aliases, editor settings, and the tools I install on every new machine.
Skill Collector 491 tok · · Q15