debug-assistant

debug-assistant is a skill for Claude Code, Codex from richardcb/oh-my-gemini. It costs 39 tokens per session (1,690 once invoked), scanned A, original, MIT.

A structured guide for investigating software bugs and unexpected behavior. It uses evidence, reproduction steps, possible causes, and tests to identify the underlying problem.

In plain words
What is it for?
Use it when a user reports a bug, tests fail, an application behaves unexpectedly, or an error needs to be reproduced and fixed.
Why use it?
It turns vague errors into a repeatable investigation and helps distinguish the real cause from guesses.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when a user reports a bug, tests fail, an application behaves unexpectedly, or an error needs to be reproduced and fixed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/richardcb/oh-my-gemini/debug-assistant
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.

Any agent
npx skills add richardcb/oh-my-gemini --skill debug-assistant
Clone the repo
git clone --depth 1 https://github.com/richardcb/oh-my-gemini

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for debug-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/debug-assistant.svg)](https://agentmods.dev/skills/richardcb/oh-my-gemini/debug-assistant)
Your own site
<a href="https://agentmods.dev/skills/richardcb/oh-my-gemini/debug-assistant"><img src="https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/debug-assistant.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,690 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.01690
Opus 5 $0.00019 $0.00845
Sonnet 5 $0.00008 $0.00338
Haiku 4.5 $0.00004 $0.00169

Measured 7d ago against content hash 3d425ec76187, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

debug-assistant 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 7d 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.

skills/debug-assistant/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Assistant Skill

Goal

Provide systematic debugging support through structured analysis, hypothesis generation, and methodical testing to identify and fix bugs efficiently.

Activation Triggers

  • User reports an error or bug
  • User says "debug", "fix this error", "why isn't this working"
  • Test failures need investigation
  • Unexpected behavior reported

Debugging Framework

1. Gather Information

# Get error context
echo "=== Recent Error Logs ==="
tail -50 *.log 2>/dev/null || echo "No log files"

# Check test output
echo "=== Test Failures ==="
npm test 2>&1 | tail -50 || echo "No test command"

# Check TypeScript errors
echo "=== Type Errors ==="
npm run typecheck 2>&1 | tail -30 || tsc --noEmit 2>&1 | tail -30 || echo "No typecheck"

# Check runtime errors
echo "=== Console Errors ==="
# User needs to provide these

2. Reproduce the Bug

Questions to ask:

  1. What is the expected behavior?
  2. What is the actual behavior?
  3. What are the exact steps to reproduce?
  4. When did this start happening?
  5. What changed recently?

Reproduction checklist:

# Check recent changes
git log --oneline -10

# Check what files changed
git diff HEAD~5 --name-only

# Check if it reproduces in a fresh state
npm ci && npm run build && npm test

3. Form Hypotheses

Based on the error, generate possible causes:

Symptom Possible Causes
TypeError: undefined Missing null check, async timing, wrong import
Network error API down, wrong URL, CORS, auth expired
Test timeout Infinite loop, missing async/await, slow DB
Build failure Type mismatch, missing dependency, syntax error
Runtime crash Memory leak, stack overflow, unhandled promise

4. Investigate Systematically

For Each Hypothesis:

A. Identify relevant code

# Find files related to the error
grep -rn "errorKeyword" src/ --include="*.ts" | head -20

# Find function definitions
grep -rn "functionName" src/ --include="*.ts" | head -10

Read the full file on GitHub · 285 lines

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. 7d ago First seen · 285 lines · 39 tokens per session scan A 3d425ec76187

Subscribe to this mod's changes

debug-assistant is a skill published in the GitHub repository richardcb/oh-my-gemini (16 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 1,690 once invoked, about $0.0002 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.