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.
npx skills add gtapps/hermitd --skill diagnosing-bugsgit clone --depth 1 https://github.com/gtapps/hermitdWrote 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/skills/gtapps/hermitd/diagnosing-bugs)<a href="https://agentmods.dev/skills/gtapps/hermitd/diagnosing-bugs"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/diagnosing-bugs/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/skills/gtapps/hermitd/diagnosing-bugs"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/diagnosing-bugs.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 | $0.00072 | $0.02163 |
| Opus 5.5 | $0.00029 | $0.00865 |
| Sonnet 5.5 | $0.00014 | $0.00433 |
| Haiku 4.5 | $0.00007 | $0.00216 |
Grade A, and why
diagnosing-bugs 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 11d 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.
Phase 1 is done when the loop is **tight** and **red-capable**: you can name **one command** — a script path, a test invocation, a curl — that you have **already run at least once** (paste the invocation and its output), This is a copy
83% identical to diagnosing-bugs — 81 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnosing Bugs
A discipline for hard bugs. Skip phases only when explicitly justified.
When exploring the codebase, consult .hermit/compiled/ (hermit knowledge base — architecture decisions and codebase health assessments) to build a mental model of relevant modules before reading source. Check any ADRs in the area you're touching.
Diagnostic byproducts (failing-test output, stack traces, repro snapshots, instrumentation logs) go in .hermit/raw/ — ephemeral inputs under analysis, not .hermit/compiled/. Reusable lessons from the diagnosis go to auto-memory.
Phase 1 — Build a feedback loop
This is the skill. Everything else is mechanical. If you have a tight pass/fail signal for the bug — one that goes red on this bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you.
Spend disproportionate effort here. Be aggressive. Be creative. Refuse to give up.
Ways to construct one — try them in roughly this order
- Failing test at whatever seam reaches the bug — unit, integration, e2e.
- Curl / HTTP script against a running dev server.
- CLI invocation with a fixture input, diffing stdout against a known-good snapshot.
- Headless browser script (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network.
- Replay a captured trace. Save a real network request / payload / event log to disk (in
.hermit/raw/); replay it through the code path in isolation. - Throwaway harness. Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.
- Property / fuzz loop. If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
- Bisection harness. If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can
git bisect runit. - Differential loop. Run the same input through old-version vs new-version (or two configs) and diff outputs.
- HITL bash script. Last resort. If a human must click, write a script that documents the exact steps and captures output so the loop is still structured.
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.
- 11d ago First seen · 144 lines · 72 tokens per session scan A f7dca1c6daac
diagnosing-bugs is a skill published in the GitHub repository gtapps/hermitd (79 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 2,163 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 83% identical to diagnosing-bugs, differing in 81 lines, and is treated as a copy.
Other skills, from other repositories
fix-bug
Run the Fix Validation pipeline to investigate, fix, and validate a bug. Ensures deterministic pipeline execution with IssueAnalyzer, FixWriter, TestWriter (conditional), TestAudit (conditional), and FixValidator stages.
dogfood
Fix-through loop: invoke a new thing, fix until it works.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
bug-fixer
A bug reproduces, the expected behaviour is clear, and the fix stands apart from the current work.
triage-issue
Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report.