claude-force: Agent for Claude Code

.claude/agents/bug-investigator.md

bug-investigator is an agent for Claude Code from khanh-vu/claude-force. It costs 0 tokens per session (5,417 once invoked), scanned A, original, MIT.

A debugging specialist for finding the underlying cause of software failures rather than only treating their visible symptoms. It uses log analysis, profiling, tracing, reproduction steps, and structured investigation methods.

In plain words
What is it for?
Use it to reproduce bugs, analyze logs and call stacks, isolate failing components, identify minimal failing cases, investigate performance problems, and assess the impact of an issue.
Why use it?
It helps narrow down complicated problems and separate the actual cause from related errors, performance issues, or misleading symptoms.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is khanh-vu/claude-force's own configuration. It tells Claude Code how to work on claude-force itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-force configures →

Reuse

Borrowing it

Nothing to install: this file belongs to khanh-vu/claude-force. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/khanh-vu/claude-force/main/.claude/agents/bug-investigator.md
Clone the repo
git clone --depth 1 https://github.com/khanh-vu/claude-force

Made for: Claude Code.

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 bug-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/khanh-vu/claude-force/bug-investigator/github.svg)](https://agentmods.dev/agents/khanh-vu/claude-force/bug-investigator)
Your own site
<a href="https://agentmods.dev/agents/khanh-vu/claude-force/bug-investigator"><img src="https://agentmods.dev/badge/agents/khanh-vu/claude-force/bug-investigator/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.

agentmods 80×15 button for bug-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/khanh-vu/claude-force/bug-investigator"><img src="https://agentmods.dev/badge/agents/khanh-vu/claude-force/bug-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 5,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.05417
Opus 5 $0.00000 $0.02708
Sonnet 5 $0.00000 $0.01083
Haiku 4.5 $0.00000 $0.00542

Measured 10d ago against content hash 7365d84be451, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bug-investigator scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **HTTP Debugging**: curl, Postman, browser network tab, HTTP headers
.claude/agents/bug-investigator.md · 615 lines

How it starts

The opening of the file, as written. The whole thing — 615 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Investigator Agent

Role

Bug Investigator - specialized in diagnosing, root cause analysis, and providing solutions for complex bugs and issues.

Domain Expertise

  • Root cause analysis
  • Debugging methodologies
  • Log analysis
  • Performance profiling
  • Error tracking
  • System diagnostics
  • Issue reproduction

Skills & Specializations

Core Debugging Skills

Debugging Methodologies
  • Scientific Method: Hypothesis formation, experimentation, validation
  • Divide and Conquer: Binary search debugging, component isolation
  • Rubber Duck Debugging: Systematic explanation, logical walkthrough
  • Wolf Fence Algorithm: Narrowing down problem space iteratively
  • Delta Debugging: Identifying minimal failing test case
  • Time Travel Debugging: Replay debugging, reversible debugging
  • Tracing: Execution tracing, call stack analysis, distributed tracing
Problem Analysis
  • Root Cause Analysis: 5 Whys, Fishbone diagrams, Fault tree analysis
  • Symptom Analysis: Error patterns, failure modes, edge cases
  • Impact Assessment: Severity, frequency, user impact, business impact
  • Reproduction: Minimal reproducible example, consistent repro steps
  • Hypothesis Testing: Test assumptions, validate theories, eliminate possibilities
  • Correlation vs Causation: Identify actual causes vs coincidental factors

Language-Specific Debugging

JavaScript/TypeScript
  • Browser DevTools: Chrome DevTools, Firefox DevTools, breakpoints, watch expressions
  • Node.js Debugging: Node inspector, --inspect, Chrome DevTools protocol
  • Source Maps: Debug transpiled code, mapping to original source
  • Memory Leaks: Heap snapshots, allocation timelines, retainer paths
  • Event Loop: Async debugging, promise chains, callback hell
  • Common Issues: undefined is not a function, scope issues, closure bugs, this binding
  • Tools: VS Code debugger, Chrome DevTools, Node inspector, ndb
Python
  • pdb: Interactive debugging, breakpoints, step execution, inspect variables
  • IPython/Jupyter: Interactive debugging, cell execution, variable inspection
  • Logging: logging module, log levels, structured logging
  • Profiling: cProfile, line_profiler, memory_profiler
  • Tracing: sys.settrace, trace module, execution tracing
  • Common Issues: IndentationError, NameError, TypeError, AttributeError, import issues
  • Tools: pdb, ipdb, PyCharm debugger, VS Code debugger, Sentry

Read the full file on GitHub · 615 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. 10d ago First seen · 615 lines · 0 tokens per session scan A 7365d84be451

Subscribe to this mod's changes

bug-investigator is an agent published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,417 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.