review-agent-setup
Helps your agent set up secure code reviews. It ensures code changes are reliably approved, creating a secure audit trail.
What it does
This tool ensures a human approves important robot (AI agent) actions before they happen. It creates a secure, verifiable record of who approved what.
When to use it
- ✓When a robot is about to comment on, approve, or merge a pull request.
- ✓When a robot will change important automation (CI) settings.
- ✓When a robot is going to publish new project releases.
Example of what to ask your AI
“Please approve the review for this code.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You need to create a special file before the robot's action and remove it afterward. This signals your approval. Each approved action generates a secure digital receipt.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add wshobson/agents --skill review-agent-setupOr download just the file:
curl -L https://raw.githubusercontent.com/wshobson/agents/main/plugins/review-agent-governance/skills/review-agent-setup/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
review-agent-governance — Setup
Gate AI agent review actions (PR reviews, comments, merges, CI edits) behind explicit human approval. Every attempt, approved or denied, produces an Ed25519-signed receipt.
When to use this plugin
Install it in projects where a Claude Code agent:
- Reviews, comments on, or merges pull requests (
gh pr review,gh pr merge) - Triages issues (
gh issue comment,gh issue close) - Publishes releases (
gh release create) - Modifies CI configuration (
.github/workflows/,.gitlab-ci.yml) - Pushes to protected branches (
main,master,release,production) - Posts to external notification surfaces (Slack webhooks, Discord), once you add a rule for the command that posts (the default policy does not gate them)
If the agent is only doing local file edits and running tests, this plugin is
overkill. Use protect-mcp for general tool-call policy enforcement and skip
this one.
One-time setup
1. Install the plugin
claude plugin install wshobson/agents/review-agent-governance
2. Copy the default policy to your project
cp .claude/plugins/review-agent-governance/policies/review-agent-governance.cedar \
./review-governance.cedar
You can edit this file to match your project's specific rules. See
../agents/review-policy-author.md for guidance on authoring review
policies.
3. Create a receipts directory and sign key
mkdir -p ./review-receipts
echo "/review-receipts/" >> .gitignore
echo "/review-governance.key" >> .gitignore
echo "/.review-approved" >> .gitignore
if [ ! -e ./review-governance.key ]; then
d=$(mktemp -d) && npx protect-mcp@0.7.4 init --dir "$d" && mv "$d/keys/gateway.json" ./review-governance.key
fi
protect-mcp 0.7.4 sign does not create the key, so the last command creates
it, and it never replaces an existing key. Without a key, the receipts are
unsigned. To rotate the key, archive ./review-governance.key and
./review-receipts/receipts.jsonl first, then run the command again. Give auditors the publicKey
value from ./review-governance.key. Do not commit the file, because it also
holds the private key.
Per-session workflow
The Cedar policy denies review-surface actions unconditionally. To approve a specific action, open an approval window before it and close it after.
Flag file (simplest)
# Before the action you want to approve
touch ./.review-approved
# Let Claude Code run the review / comment / merge
# Immediately after
rm ./.review-approved
Slash command (from within Claude Code)
/approve-review "Reviewing PR #123 authored by contributor X"
This creates ./.review-approved with the given reason embedded as a note,
and records the reason in an unsigned approval log under
./review-receipts/approvals/. A follow-up rm is still needed to close the
window.
Dry-run everything (force full policy evaluation)
If you want every tool call to go through Cedar with no approval bypass:
export REVIEW_APPROVAL_FLAG=./.never-approve
Any tool call matching a forbid rule will be denied; approved windows have no effect. Useful for CI or for a locked-down audit run.
Verifying the receipts
List all receipts:
ls -la ./review-receipts/
Verify every receipt offline with the public key:
PUB=$(node -p 'JSON.parse(require("fs").readFileSync("./review-governance.key")).publicKey')
npx @veritasacta/verify@0.9.2 --replay-chain ./review-receipts/receipts.jsonl --key "$PUB"
Exit 0 means every receipt verified. Exit 1 means a receipt failed verification, because it was tampered with, the key is wrong, or a line is malformed. Exit 2 means the receipts file could not be read.
A denied call never runs, so it has no receipt. To see what the policy blocked, run this inside Claude Code:
/list-pending
It lists the tool calls that the PreToolUse hook blocked in the current session, with the tool name and the command or path.
Example: approving a PR review
# 1. Human reviews the agent's proposed comment
$ /list-pending
Blocked in this session:
- Bash "gh pr review 42 --approve --body 'LGTM'"
- Bash "gh pr comment 42 --body 'Looking good'"
# 2. Human decides the first one is appropriate, approves it
$ /approve-review "Approving LGTM on PR 42 after visual inspection"
./.review-approved created
# 3. Agent retries the action; this time it succeeds
$ agent: gh pr review 42 --approve --body "LGTM"
…
FAQ
What are 'pull requests'?
These are requests to add or change code in a project, usually reviewed by others before being accepted.
What is 'CI'?
CI stands for Continuous Integration. It's an automatic process that tests code whenever it's changed to ensure everything is working.
How do I know the approval is secure?
Each approval generates a digital receipt signed with technology called Ed25519, which is hard to fake and can be verified by anyone with the public key.
Details
Original description by the author
Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.
repo: wshobson/agents
Popularity
- GitHub stars
- 41k
- Ranking position
- #4944
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
screen-reader-testing
Has your agent test websites using screen readers to ensure they are accessible.
wshobson/agents
wcag-audit-patterns
Helps your agent audit websites for accessibility and fix issues according to WCAG guidelines.
wshobson/agents
multi-reviewer-patterns
Enables your agent to coordinate parallel code reviews, deduplicating findings and consolidating reports.
wshobson/agents
parallel-debugging
Allows the agent to debug complex issues with parallel investigations and root cause analysis.
wshobson/agents
Similar skills
django-security
Helps your agent implement security practices in Django applications. It focuses on authentication, authorization, and prevention against common attacks, ensuring more secure code.
affaan-m/ECC
laravel-security
Helps your agent secure Laravel applications against threats. Implements security practices for authentication, authorization, and common attack prevention.
affaan-m/ECC
module-regression
Helps your agent manage changes in large projects. Ensures code changes in one part don't break other parts.
affaan-m/ECC