⚖ Agent Referee

    1

    Repository-level governance and lifecycle management for AI agents using structured hooks, audits, and specs.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    ⚖ Agent Referee

    Example session with this skill installed

    Run an audit on the last 20 sessions to see why the router keeps missing the 'ship' skill.

    • Read your context and instructions
    • Compiled the agent referee

    I have audited the last 20 sessions and the trigger evaluations.

    Session Audit & Postmortem Report

    MetricValue
    Sessions Scanned20
    Router Precision85%
    'ship' Skill Misses3
    Most Frequent Failurerouted-skill-loaded ✗

    Postmortem: 'ship' routing failure

    What happened: The user asked to "push these changes to a new branch," but the agent performed a standard git commit without loading the ship skill.
    Why: The router (.referee/routing.json) lacks a pattern for "push these changes." The request was handled by the default agent behavior instead of the structured ship workflow.
    Fix (Router Layer): Added "push these changes" and "new branch" to the trigger patterns in .referee/routing.json.

    Trigger Evaluation Results

    node .referee/scripts/eval-triggers.mjs --live
    [PASS] "full send" -> ship
    [PASS] "fix this bug" -> ship
    [FAIL] "push these changes" -> (none) [Expected: ship]
    [FIXED] Updated .referee/routing.json with 2 new patterns.
    

    Next steps

    1. Run node .referee/scripts/eval-triggers.mjs to verify the new routing patterns.
    2. Review .referee/audits/session-bf23.md for a detailed trace of the last missed routing event.
    3. Delete the redundant deploy-helper skill; it has had 0 loads in 20 sessions.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Stop guessing why your AI agents are failing or hallucinating. Agent Referee is a suite of 13 specialized skills designed to enforce guardrails, audit performance, and manage the entire development lifecycle within your repository. It moves agent governance from vague prompts into verifiable system hooks and structured knowledge.

    What it does

    • Enforces Guardrails via .referee/scripts/hooks/guard.mjs to block unauthorized edits to protected paths, secrets, or main branch merges.
    • Audits Performance by running postmortems on agent failures, tracking skill load frequency, and identifying redundant or weak instructions.
    • Standardizes Shipping with a structured "Ship" workflow that covers branching, planning, testing, and PR generation with human-readable evidence.
    • Captures Knowledge in a kb/ directory to store technical decisions, task history, and lessons learned that code alone cannot express.
    • Validates Output using a "Verification Before Completion" protocol that requires fresh command output and test results before any claim of success.

    How it works

    1. Onboard: Run referee-onboard to scan the codebase and configure repository-specific protections in .referee/config.json.
    2. Spec: Use spec-first to agree on test cases in plain English with the user before a single line of code is written.
    3. Execute: The agent follows the ship or writing-plans skill to implement changes, strictly adhering to the "Explore before change" rule.
    4. Review: Invoke the review-loop to trigger an independent subagent or CLI reviewer for a second opinion on the diff.
    5. Audit: Periodically run method-upkeep to clean up stale skills, fix routing misses, and review session logs.

    Frameworks & tools

    Built for environments using Claude Code, Cursor, or custom agent harnesses. It utilizes a Node.js runtime for evaluation scripts and integrates with the GitHub CLI for PR management.

    Why this beats prompting it yourself

    Prompting "don't touch my .env file" fails when context gets long. This skill uses a hard-coded script hook (guard.mjs) to physically block the shell command, making safety a system property rather than a suggestion.

    Use cases

    • Preventing agents from editing critical infrastructure or legacy migrations.
    • Automatically generating high-quality PR descriptions with evidence and agent tags.
    • Reducing agent loop costs by enforcing plan-first and spec-first workflows.
    • Onboarding new agents to complex repos with existing architectural decisions.

    Known limitations

    Requires a Node.js environment to run the referee scripts and hooks. Protections only work if the agent harness respects the provided hook scripts.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires Node.js runtime for script-based hooks and audits. Protective guards require the agent harness to execute hook scripts before shell/file operations.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 11 days ago

    • Free with an Agensi account

    Software
    PythonGitturboNode.js

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed11 days ago

    What's inside

    Frequently Asked Questions

    Agent Referee replaces unreliable prompt-based instructions with hard-coded script hooks and structured validation protocols. It physically blocks unauthorized actions, such as editing sensitive files or merging without tests, ensuring your agents follow repository rules consistently.

    The skill is designed for terminal-based AI environments like Claude Code, Cursor, and custom agent harnesses. It requires a Node.js runtime to execute its verification scripts and integrates with the GitHub CLI for automated PR management and auditing.

    You receive a comprehensive suite of 13 specialized skills, including tools for onboarding, automated code review, specification-first planning, and a structured "Ship" workflow. It also includes the `.referee` configuration framework and a set of Node.js-based hooks for repository protection.

    No, Agent Referee is designed to be unobtrusive. It initializes a `.referee/` directory and a `kb/` folder to store configurations and technical decisions, keeping the governance logic separate from your primary application code.

    The `referee-onboard` skill automatically scans your repository to identify critical files and branch structures. From there, you can customize the `.referee/config.json` to define specific guardrails, such as blocking edits to legacy migrations or enforcing specific test coverage requirements.

    New in Agents & Orchestration

    Free