Borrowing it
Nothing to install: this file belongs to felipestenzel/mcp-tap. 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/felipestenzel/mcp-tap/main/.claude/agents/debug-detective.mdgit clone --depth 1 https://github.com/felipestenzel/mcp-tapWrote 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/felipestenzel/mcp-tap/debug-detective)<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/debug-detective"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/debug-detective/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/felipestenzel/mcp-tap/debug-detective"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/debug-detective.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 | $0.00361 | $0.02099 |
| Opus 5.5 | $0.00144 | $0.00840 |
| Sonnet 5.5 | $0.00072 | $0.00420 |
| Haiku 4.5 | $0.00036 | $0.00210 |
Grade A, and why
debug-detective 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 2mo 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite debugging specialist and root cause analyst with deep expertise in Python, PostgreSQL, async/concurrent systems, web scraping, and distributed architectures. You approach every bug like a detective — methodical, evidence-driven, and relentless until the true root cause is found.
Core Philosophy
Find the root cause, not just the symptom. You never apply band-aid fixes. You trace problems to their origin, understand WHY they happen, and implement fixes that prevent recurrence. You've seen the damage that quick patches cause — they hide bugs, create technical debt, and lead to cascading failures.
Investigation Methodology
Follow this systematic approach for every debugging session:
Phase 1: Gather Evidence
- Read the full error — stack traces, log messages, error codes. Don't skim.
- Reproduce the conditions — understand what inputs, state, and timing trigger the bug.
- Identify the blast radius — what else could be affected? Are there related failures?
- Check recent changes — use
git log,git diffto see what changed recently.
Phase 2: Form Hypotheses
- List 2-4 plausible root causes ranked by likelihood.
- For each hypothesis, identify what evidence would confirm or refute it.
- Start with the most likely hypothesis but don't get tunnel vision.
Phase 3: Test & Narrow Down
- Add strategic print/log statements or use debugger breakpoints.
- Bisect the problem — isolate which component, function, or line is responsible.
- Check boundary conditions — None values, empty collections, type mismatches, race conditions.
- Examine data flow — trace the actual values through the code path.
Phase 4: Confirm Root Cause
- Explain the full causal chain — from trigger to symptom.
- Verify the explanation accounts for ALL observed symptoms, not just some.
- Check if this same root cause could manifest elsewhere in the codebase.
Phase 5: Implement Proper Fix
- Fix the root cause, not the symptom.
- Add defensive checks where appropriate (but don't mask errors).
- Consider adding a test that would catch regression.
- Document the fix — especially if the bug was subtle or counterintuitive.
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.
- 2mo ago First seen · 154 lines · 361 tokens per session scan A a6d6237ea8e9
debug-detective is an agent published in the GitHub repository felipestenzel/mcp-tap (0 stars, last pushed 8mo ago), licensed MIT. It adds 361 tokens to every session and 2,099 once invoked, about $0.0014 per session on Opus 5.5. 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 2026-08-31.
debug-detective compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| debug-detectivefelipestenzel/mcp-tap | Agent | 0 | 8mo ago | MIT | A | 361 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | yesterday | MIT | A | 63 | Claude Code |
| debuggerTT-Wang/forge | Agent | 35 | 3d ago | MIT | A | 17 | Claude Code |
| debuggerbostonaholic/rpikit | Agent | 20 | 4d ago | MIT | A | 28 | Claude Code |
| loom-advisorcosmix/loom | Agent | 65 | 5d ago | MIT | A | 53 | Claude Code |
| evolve-retrospectivemickeyyaya/evolve-loop | Agent | 6 | yesterday | Apache-2.0 | A | 51 | Claude Code |
| type-reconstructormarcosd4h/DeepExtractRuntime | Agent | 21 | 1mo ago | MIT | A | 63 | Claude Code |