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.
field: Developer tools
ARCHETYPE
Automator
Hooks on every lifecycle event: format, lint, notify, log.
Copy this rig
# review before running: this installs third-party code
$ npx degit mlophez/polix-ai/.claude ./rig-polix-ai # inspect, then merge into .claude/ 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 mlophez/polix-ai/plugins/polix/skills/add-rule .claude/skills/add-rule $ npx degit mlophez/polix-ai/plugins/polix/skills/audit .claude/skills/audit $ npx degit mlophez/polix-ai/plugins/polix/skills/doctor .claude/skills/doctor $ npx degit mlophez/polix-ai/plugins/polix/skills/init .claude/skills/init $ npx degit mlophez/polix-ai/plugins/polix/skills/plan .claude/skills/plan $ npx degit mlophez/polix-ai/plugins/polix/skills/review .claude/skills/review $ npx degit mlophez/polix-ai/plugins/polix/skills/workflow .claude/skills/workflow
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Edit|Write|MultiEdit|NotebookEdit|Bash",
"hooks": [
{
"type": "command",
"command": "polix hook claude"
}
]
}
]
}
} Skills (7)
Hooks (9)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | polix hook claude |
| SessionStart | startup | polix update --hook |
| UserPromptSubmit | * | polix hook claude |
| PreToolUse | Edit|Write|MultiEdit|NotebookEdit|Bash | polix hook claude |
| PostToolUse | Edit|Write|MultiEdit|NotebookEdit|Bash | polix hook claude |
| PostToolUseFailure | Edit|Write|MultiEdit|NotebookEdit|Bash | polix hook claude |
| SubagentStop | * | polix hook claude |
| Stop | * | polix hook claude |
| SubagentStart | * | polix hook claude |
Similar rigs
archcore-ai/archcore
Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.
Minimalist 337 tok · · Q0
machiko/agent-working-agreements
Incident-backed working agreements for AI coding agents
Pragmatist 243 tok · · Q0
yigitkonur/plugin-trigger-dev
Claude Code plugin for Trigger.dev: scenario-aware build/chat-agent/diagnose skills, init/new/audit/ship/doctor commands, a prod-environment guard and an edit tripwire. Includes the official Trigger.dev MCP server.
Pragmatist 5.4k tok · · Q10
sravan27/context-os
Cut Claude Code token usage by 40.9% and ship a CI gate for coding-agent cost leaks. Stdlib Python hook + GitHub Action for Claude Code, Codex, Cursor, and agentic coding teams.
Pragmatist 680 tok · · Q0