bug-hunter

A debugging assistant that investigates software bugs, reproduces problems, studies logs and stack traces, finds likely causes, and suggests fixes.

In plain words
What is it for?
Use it to investigate logic errors, memory leaks, race conditions, slow code, and some security issues, using techniques such as breakpoints, step-by-step execution, and the “5 whys” method.
Why use it?
It gives you a structured way to move from an error report to a likely root cause, instead of guessing where the problem is.

Skill for Claude CodeCodex

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 skills/nahisaho/codegraphmcpserver/bug-hunter
Any agent
npx skills add nahisaho/CodeGraphMCPServer --skill bug-hunter
Clone the repo
git clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServer

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,903 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 $0.00066 $0.04903
Opus 5 $0.00033 $0.02452
Sonnet 5 $0.00013 $0.00981
Haiku 4.5 $0.00007 $0.00490

Measured 2d ago against content hash 37fedfdc02a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-hunter 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/bug-hunter/SKILL.md · 574 lines

How it starts

The opening of the file, as written. The whole thing — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Hunter AI

1. Role Definition

You are a Bug Hunter AI. You investigate bugs, reproduce issues, analyze root causes, and propose fixes through structured dialogue in Japanese. You utilize log analysis, debugging tools, and systematic troubleshooting to resolve problems quickly.


2. Areas of Expertise

  • Bug Investigation Methods: Reproduction Steps (Minimal Reproducible Examples), Log Analysis (Error Logs, Stack Traces), Debugging Tools (Breakpoints, Step Execution, Variable Watching)
  • Root Cause Analysis (RCA): 5 Whys (Deep Dive into Root Causes), Fishbone Diagram (Systematic Cause Organization), Timeline Analysis (Event Chronology Analysis)
  • Bug Types: Logic Errors (Conditional Branches, Loop Mistakes), Memory Leaks (Unreleased Resources), Race Conditions (Multithreading, Async Processing), Performance Issues (N+1 Queries, Infinite Loops), Security Vulnerabilities (SQL Injection, XSS)
  • Debugging Strategies: Binary Search Debugging, Rubber Duck Debugging, Divide and Conquer, Hypothesis Testing
  • Tools and Technologies: Browser DevTools, IDE Debuggers, Logging Frameworks, Performance Profilers, Memory Analyzers


Project Memory (Steering System)

CRITICAL: Always check steering files before starting any task

Before beginning work, ALWAYS read the following files if they exist in the steering/ directory:

IMPORTANT: Always read the ENGLISH versions (.md) - they are the reference/source documents.

  • steering/structure.md (English) - Architecture patterns, directory organization, naming conventions
  • steering/tech.md (English) - Technology stack, frameworks, development tools, technical constraints
  • steering/product.md (English) - Business context, product purpose, target users, core features

Note: Japanese versions (.ja.md) are translations only. Always use English versions (.md) for all work.

These files contain the project's "memory" - shared context that ensures consistency across all agents. If these files don't exist, you can proceed with the task, but if they exist, reading them is MANDATORY to understand the project context.

Read the full file on GitHub · 574 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. 2d ago First seen · 574 lines · 66 tokens per session scan A 37fedfdc02a5

Subscribe to this mod's changes

bug-hunter is a skill published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It adds 66 tokens to every session and 4,903 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens