sandalkuilang/sapu
Autonomous backlog sweeps, audits and red-team passes for Claude Code, driven by a per-repo contract.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
$ git clone --depth 1 https://github.com/sandalkuilang/sapu 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 sandalkuilang/sapu/plugins/sapu/skills/argus .claude/skills/argus $ npx degit sandalkuilang/sapu/plugins/sapu/skills/dream .claude/skills/dream $ npx degit sandalkuilang/sapu/plugins/sapu/skills/forge .claude/skills/forge $ npx degit sandalkuilang/sapu/plugins/sapu/skills/init .claude/skills/init $ npx degit <redacted> .claude/skills/inspector $ npx degit sandalkuilang/sapu/plugins/sapu/skills/journey .claude/skills/journey $ npx degit sandalkuilang/sapu/plugins/sapu/skills/momus .claude/skills/momus $ npx degit sandalkuilang/sapu/plugins/sapu/skills/nemesis .claude/skills/nemesis $ npx degit sandalkuilang/sapu/plugins/sapu/skills/sapu .claude/skills/sapu
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 (9)
Similar rigs
bentleypark/claude-code-mobile-spine
Claude Code plugin marketplace bundling mobile-spine — scaffolds a meta-repo coordinating 4 subagents (api/pm/android/ios) for mobile teams whose Android, iOS, and Backend live in 3 separate repos.
Minimalist 84 tok · · Q15
maxwellmattryan/forge
A lightweight, self-improving software factory for AI coding agents (as a Claude Code plugin) 🏗️
Pragmatist 7.3k tok · · Q10
glenbenatiro/ai-os-playbook
A portable, LLM-agnostic playbook for building AI Operating Systems: Obsidian-readable markdown vaults that an LLM maintains as its kernel, so your agent never forgets your context.
Pragmatist 3.7k tok · · Q3
yongkyung-oh/agent-bootstrap
A minimal workflow bootstrap for AI coding agents — three markdown files that solve context loss between sessions. No framework, no dependencies.
Minimalist 1.7k tok · · Q8