← Browse
codex-as-critic-guardrail
JarrydAdaens ★ 1
This Claude Code plugin implements an actor-critic safety guardrail that gates the executor's first file write behind a mandatory read-only consultation with a Codex CLI critic, surfacing blindspots common to same-family models. The critic is probed for health on session start, and consultation succeeds via a local Python script that pipes structured JSON to the critic backend with configurable timeouts.
Install
> /plugin marketplace add JarrydAdaens/agentic_rails_marketplace/tree/HEAD/plugins/claude/codex-as-critic-guardrail
> /plugin install codex-as-critic-guardrail
What it's made of
3 skills · 4 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 3
- MCP servers
- 0
- Hooks
- 4 · PostToolUse, PreToolUse, SessionStart
What it needs & plugs into
- API keys
- none
- Paid services
- Codex
- External tools
pythonrunpy.run_path(os.path.join(d,'critic_cleanup.py'),run_name='__main__')"runpy.run_path(os.path.join(d,'critic_context.py'),run_name='__main__')"runpy.run_path(os.path.join(d,'critic_gate.py'),run_name='__main__')"runpy.run_path(os.path.join(d,'critic_marker.py'),run_name='__main__')"sys.path.insert(0,d)- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (JarrydAdaens).