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.
curl -O https://raw.githubusercontent.com/khanh-vu/claude-force/main/.claude/agents/bug-investigator.mdgit clone --depth 1 https://github.com/khanh-vu/claude-forceWrote 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/agents/khanh-vu/claude-force/bug-investigator)<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.
<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>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 | $0.00000 | $0.05417 |
| Opus 5 | $0.00000 | $0.02708 |
| Sonnet 5 | $0.00000 | $0.01083 |
| Haiku 4.5 | $0.00000 | $0.00542 |
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 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,thisbinding - 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
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 · 615 lines · 0 tokens per session scan A 7365d84be451
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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.