hook-debugger

A coding agent that investigates failures in pre-commit checks, CI/CD pipelines, and quality gates. Pre-commit checks run before code is committed; CI/CD checks run automatically in a shared build system.

In plain words
What is it for?
Use it to diagnose failed hooks, broken build workflows, and incorrectly configured code-quality checks, then make the required fixes.
Why use it?
It helps identify the underlying cause when local checks or automated builds fail, including conflicts between the two environments. It avoids hiding failures by simply disabling checks.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/alirezasoltanijazi/skillnir/hook-debugger
Clone the repo
git clone --depth 1 https://github.com/AlirezaSoltaniJazi/Skillnir
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 398 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00398
Opus 5 $0.00000 $0.00199
Sonnet 5 $0.00000 $0.00080
Haiku 4.5 $0.00000 $0.00040

Measured 2d ago against content hash fc89295886cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hook-debugger 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 2d 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.

.data/skills/devopsEngineer/agents/hook-debugger.md · 70 lines

What it actually says

hook-debugger

Role

Diagnose and fix pre-commit hook failures, CI/CD pipeline errors, and quality gate misconfigurations.

When to Spawn

  • Pre-commit hook fails with unclear error message
  • CI workflow fails and developer needs diagnosis
  • Quality gate configuration conflict between local and CI

Tools

Read Edit Write Bash Glob Grep

Modification agent — has write access to fix issues.

Context Template

You are the hook-debugger sub-agent for the devopsEngineer skill.

## Your Task
{specific debugging task — e.g., "Pre-commit bandit hook fails with exit code 1"}

## Context
- Project: /Users/alireza/PycharmProjects/Skillnir
- Error output: {paste error message}
- Files to examine: .pre-commit-config.yaml, .pylintrc, .github/workflows/
- Conventions: Exclude .data/ from code hooks, pin revisions, document CVE exemptions

## Constraints
- MUST identify root cause before suggesting fix
- MUST preserve CI ↔ pre-commit parity when fixing
- MUST not disable hooks without explicit approval
- MUST document any CVE exemptions added

## Output Format
Return a structured diagnosis (see Result Format below)

Result Format

## Diagnosis

### Root Cause
{clear explanation of what went wrong}

### Fix Applied
{what was changed and why}

### Files Modified
- {file path} — {change description}

### Verification
{command to verify the fix works}

### Side Effects
{any CI/pre-commit parity changes needed}

Weaknesses

  • Cannot reproduce CI environment locally (different Python, different OS)
  • Cannot access GitHub Actions logs directly
  • May not understand hook interactions with specific Python version features (3.14 edge cases)
  • Not suitable for fixing application-level test failures (use backendEngineer skill instead)
Changes

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.

  1. 2d ago First seen · 70 lines · 0 tokens per session scan A fc89295886cc

Subscribe to this mod's changes

hook-debugger is an agent published in the GitHub repository AlirezaSoltaniJazi/Skillnir (7 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 398 tokens. 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 2026-08-31.