LLM Skills
~/catalog/security//plugin.json
SecurityGitHub source

Review agent governance

/plugin.json

Ajoute Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config. Cedar-gated, receipt-signed,

Tom FarleyTom Farley
38.9k
May 26, 2026
MIT
// plugin content

Claude Code plugin indexed at GitHub. Source description: Requires human approval before an AI agent can post PR reviews, comments, merges, or write to CI configuration. Cedar-gated and receipt-signed, designed to prevent the "Hermes" failure mode where a review bot posts without oversight. Detected version: 0.1.1

// original public source
wshobson/agents
/plugins/review-agent-governance/.claude-plugin/plugin.json
License: MIT
Independent project, not affiliated with Anthropic. This plugin remains the property of its original author.
// install this plugin
Paste this command in your terminal at the root of your project:
mkdir -p .claude/commands && curl -o ".claude/commands/plugin.json" "https://raw.githubusercontent.com/wshobson/agents/main/plugins/review-agent-governance/.claude-plugin/plugin.json"
Then in Claude Code, type /plugin.json to activate it.
open_in_newOpen original source
// save
Save available after sign in.
loginSign in to save
// information
CreatorTom Farley
Stars 38.9k
CategorySecurity
LicenseMIT
UpdatedMay 26, 2026
Format.md
AccessFree
// similar

Plugins Security

View allarrow_forward