---
title: "Hooks Evaluator - Air Market"
description: "You set up hooks and one of them either does nothing or freezes the agent. This goes through the hooks in your settings files, checks each command really exists, looks at how blocking ones handle exi…"
canonical: "https://airmarket.ai/app/eval-hooks"
---

[Air Market](/) / [Developer Tools](/category/devtools) / Hooks Evaluator

Skill by [Florian BRUNIAUX](/@florianbruniaux)

# Hooks Evaluator

Work out why a hook never fires, or hangs everything

## What this does

You set up hooks and one of them either does nothing or freezes the agent. This goes through the hooks in your settings files, checks each command really exists, looks at how blocking ones handle exit codes, and flags the ones with no timeout, so you can see which is at fault.

### Top 3 things it does for you

- Check my hooks are set up correctly
- Find out why a hook never runs
- Track down the hook that hangs the agent

## Information

**Hooks Evaluator at a glance**

|  |  |
| --- | --- |
| Kind | Skill |
| Publisher | [Florian BRUNIAUX](/@florianbruniaux) |
| Category | [Developer Tools](/category/devtools) |
| Works with | Agent Skills - an open standard supported by 40+ agents |
| Size | 16 KB |
| Licence | CC-BY-SA-4.0 |
| Repository | [florianbruniaux/claude-code-ultimate-guide](https://github.com/florianbruniaux/claude-code-ultimate-guide/tree/9777d5b74653dd7fac8f96e66760de3448b3513e/examples/skills/eval-hooks) |
| GitHub stars | 5,793 (as of Nov 2026) |

## Security report

**Verified.** AIR scanned this exact version of Hooks Evaluator and flagged nothing. AIR's verdict: **safe**.

**What Hooks Evaluator's check was run against**

|  |  |
| --- | --- |
| Commit | 9777d5b74653dd7fac8f96e66760de3448b3513e |
| Content hash | 52a6bb5ef2415748432554bef87158ceea06a802016b9183c3afbe2f510fb5b0 |
| Files read | [Browse the files at this exact commit](https://github.com/florianbruniaux/claude-code-ultimate-guide/blob/9777d5b74653dd7fac8f96e66760de3448b3513e/examples/skills/eval-hooks/SKILL.md) |

A scan is named by the exact content it read, not by a version number. A different version is a different artifact, and nothing here applies to a version AIR has not scanned.

[Read the full security report for Hooks Evaluator](/security/eval-hooks)

## About Hooks Evaluator

This audits the Claude Code hooks defined in settings.json files, checking that they are valid, safe for performance, and correct.

It resolves each command against the filesystem, checks the exit-code strategy for blocking hooks, flags missing timeouts, and reviews interactive versus async patterns.

Use it when setting up hooks for the first time, when debugging a hook that never fires or hangs the agent, or as a periodic hygiene pass.

## What's inside

- SKILL.md - instructions

## Questions

### Is Hooks Evaluator safe to install?

AIR scanned this exact version of Hooks Evaluator and flagged nothing. AIR's verdict: safe. The verdict is named by the content that was read, at commit 9777d5b74653, so it cannot drift onto a version nobody scanned. The full report is at https://airmarket.ai/security/eval-hooks.

### How do I install Hooks Evaluator?

Open https://airmarket.ai/app/eval-hooks on Air Market and use the install action: Air Market hands Claude a prompt naming this exact skill, and Claude sets it up. Source, pinned to the exact commit this listing describes: https://github.com/florianbruniaux/claude-code-ultimate-guide/tree/9777d5b74653dd7fac8f96e66760de3448b3513e/examples/skills/eval-hooks. Install from that link, not the branch.

## Related on Air Market

- [More Developer Tools listings](/category/devtools)
- [Everything by Florian BRUNIAUX](/@florianbruniaux)

---

Canonical URL: <https://airmarket.ai/app/eval-hooks>