machiko/agent-working-agreements
Incident-backed working agreements for AI coding agents
stack: Shell
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit machiko/agent-working-agreements/skills ./rig-agent-working-agreements/skills $ npx degit machiko/agent-working-agreements/hooks ./rig-agent-working-agreements/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 machiko/agent-working-agreements/skills/audit .claude/skills/audit $ npx degit machiko/agent-working-agreements/skills/doctor .claude/skills/doctor $ npx degit machiko/agent-working-agreements/skills/harvest .claude/skills/harvest $ npx degit machiko/agent-working-agreements/skills/record .claude/skills/record $ npx degit machiko/agent-working-agreements/skills/review .claude/skills/review $ npx degit machiko/agent-working-agreements/skills/setup .claude/skills/setup
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 (6)
Similar rigs
mlophez/polix-ai
Declarative guardrails for Claude Code: one polix.yaml decides what the agent may not touch, what must pass and what runs at every step.
Automator 1.1k tok · · Q15
stickerdaniel/browserjack
Use OpenAI's installed Codex browser runtime from Claude Code or any MCP client on macOS.
Pragmatist 2.7k tok · · Q0
vinhqbui/scholion
Version control for coding agents: decisions and dead ends anchored to code, plus token-budgeted context packs. Works with Claude Code, Codex, Gemini via MCP.
Pragmatist 6.0k tok · · Q8
Rich627/whatsapp-claude-plugin
Claude Code WhatsApp channel plugin — run AI directly from WhatsApp, voice transcription, remote tool approval, access control. No API keys, no Docker, just a linked device.
Pragmatist 4.9k tok · · Q15