Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add athola/claude-night-market/plugin install abstractWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/athola/claude-night-market/hooks-eval)<a href="https://agentmods.dev/commands/athola/claude-night-market/hooks-eval"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/hooks-eval/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/athola/claude-night-market/hooks-eval"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/hooks-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.01087 |
| Opus 5 | $0.00007 | $0.00544 |
| Sonnet 5 | $0.00003 | $0.00217 |
| Haiku 4.5 | $0.00001 | $0.00109 |
Grade A, and why
hooks-eval scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hooks-Eval
Detailed evaluation framework for analyzing all hooks within a plugin (or across project/global scopes) with advanced security scanning, performance benchmarking, and compliance validation. Built on the same principles as skills-eval but specifically tailored for Claude Code hook architecture.
Invoke Skill(abstract:hooks-eval), which carries the evaluation criteria,
the SDK hook types and the integration points.
When To Use
Use this command when you need to:
- Evaluating all hooks in a plugin comprehensively
- Comparing multiple hooks
- Validating quality gates across hook portfolio
- Security scanning entire plugin's hooks
When NOT To Use
Avoid this command if:
- Validating specific hook - use /validate-hook instead
- Creating new hooks - use /create-hook instead
Usage
# Evaluate all hooks in current plugin
/hooks-eval
# Evaluate specific plugin directory
/hooks-eval /path/to/plugin
# Security-focused evaluation
/hooks-eval --security-only
# Performance benchmarking
/hooks-eval --performance-baseline
# Compliance checking
/hooks-eval --compliance-report
# Generate detailed report
/hooks-eval --detailed --format detailed
# Cross-scope evaluation (plugin → project → global)
/hooks-eval --all-scopes
# CI/CD integration
/hooks-eval --quality-gate --format json --output results.json
Options
Scope Selection
--plugin <path>: Specific plugin directory (default: current plugin)--scope <type>: Evaluate specific scope (plugin, project, global)--all-scopes: Evaluate all scopes in priority order--include-external: Include hooks from external dependencies
Analysis Focus
--security-only: Focus exclusively on security vulnerabilities--performance-check: Analyze execution performance and resource usage--compliance-check: Validate against hook development standards--detailed: Full analysis across all dimensions (default)
Output Control
--format <type>: Output format (summary, detailed, json, sarif, dashboard)--output <file>: Write results to file--verbose: Show detailed analysis and recommendations--quiet: Minimal output, exit codes only--severity <level>: Minimum severity level to report
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 159 lines · 14 tokens per session scan A 3ba2a5182bff
hooks-eval is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 1,087 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
claudex
Claude writes, Codex reviews, iterate until both agree — then ship with love.
debate
The debate — Claude and Codex argue a design decision from opposite corners, you arbitrate.
stats
Agreement stats — how often do Claude and Codex actually agree in this repo?
diff-review
AI-powered diff review for Solana-specific issues and code quality.
demo
A two-minute guided duet — plants bugs in a throwaway repo and lets Claude and Codex argue about them.
pr-issue-resolve
Follow these steps to analyze suggested changes (e.g., review comments, inline suggestions, or requested modifications) in a GitHub Pull Request (PR) and resolve them efficiently. The goal is to review, understand, plan fixes, apply changes, test, and update the PR while maintaining code quality and collaboration.