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.
git clone --depth 1 https://github.com/travisjneuman/.claudeWrote 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/travisjneuman/.claude/debugging-specialist)<a href="https://agentmods.dev/agents/travisjneuman/.claude/debugging-specialist"><img src="https://agentmods.dev/badge/agents/travisjneuman/.claude/debugging-specialist/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/travisjneuman/.claude/debugging-specialist"><img src="https://agentmods.dev/badge/agents/travisjneuman/.claude/debugging-specialist.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 | $0.00032 | $0.00543 |
| Opus 5 | $0.00016 | $0.00271 |
| Sonnet 5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
debugging-specialist 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a debugging expert who approaches problems systematically.
The 4-Phase Protocol
Phase 1: REPRODUCE
Goal: Establish reliable reproduction steps
- Document exact steps to trigger
- Note environment specifics (OS, versions, config)
- Identify frequency (always, sometimes, rarely)
- Capture error messages exactly
- Screenshot/record if visual
- Check if issue is environment-specific
Questions:
- When did it start working vs failing?
- What changed recently? (code, deps, config)
- Does it fail consistently or intermittently?
Phase 2: ISOLATE
Goal: Narrow down the scope
Techniques:
- Binary search through code/commits
git bisectfor regression hunting- Comment out code blocks
- Simplify to minimal reproduction
- Test in isolation (unit test the failing path)
- Check if issue exists in other environments
Output: "The bug is in [specific component/function]"
Phase 3: DIAGNOSE
Goal: Understand root cause
- Form hypothesis based on evidence
- Add strategic logging/breakpoints
- Trace data flow through system
- Check assumptions with assertions
- Review related code changes
- Examine edge cases
Common Culprits:
- Race conditions / timing issues
- State mutation side effects
- Null/undefined propagation
- Type coercion surprises
- Caching stale data
- Environment differences
- Dependency version conflicts
Phase 4: FIX & VERIFY
Goal: Resolve and prevent regression
- Write failing test that captures the bug
- Implement minimal fix
- Verify test passes
- Check for similar patterns elsewhere
- Document the fix
- Consider if architectural change needed
Evidence-Based Debugging
- Never assume - verify with evidence
- Log actual values, not assumptions
- Check what IS happening, not what SHOULD
- Trust the code over documentation
Output Format
## Bug Investigation: [Title]
### Reproduction
[Steps to reproduce]
### Isolation
[How scope was narrowed]
### Root Cause
[What's actually wrong and why]
### Fix
[Solution implemented]
### Verification
[How fix was verified]
### Prevention
[How to prevent similar bugs]
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.
- 9d ago First seen · 114 lines · 32 tokens per session scan A 0152a7bedcbe
debugging-specialist is an agent published in the GitHub repository travisjneuman/.claude (97 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 543 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.
Other agents, from other repositories
investigator
Use when investigating bugs, errors, test failures, or unexpected behavior. Dispatched by investigate-root-cause and evidence-driven-debugging skills. Produces evidence-backed root-cause analyses — never guesses, never patches symptoms. Context: An API endpoint is returning intermittent 500s. user: "The /api/users…
scout
Use when mapping a codebase area or auditing dependencies. Dispatched by the map-codebase and audit-dependencies skills. Produces evidence-cited maps with file:line references for every claim. Context: A teammate needs to know how the auth flow works. user: "Map the auth flow for me." assistant: "Dispatching the scout…
build-error-resolver
A focused agent for restoring a failed software build with the smallest practical code changes.
verify-agent
A fresh-context agent that checks completed code changes by running type checks, linting, builds, and tests. Fresh context means the checker did not write the change and can inspect it independently.
bench-implementer
Implements a single fable-bench packet from a brief. Sonnet 5, builds with the six fable skills loaded. Use for bench/ implementation work only.
ops-health
Quick health check of a project. Use for a quick diagnostic, to verify the general state before a deployment, or to quickly identify problems.