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 hex/claude-council --skill bug-fixergit clone --depth 1 https://github.com/hex/claude-councilWrote 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/hex/claude-council/bug-fixer)<a href="https://agentmods.dev/skills/hex/claude-council/bug-fixer"><img src="https://agentmods.dev/badge/skills/hex/claude-council/bug-fixer/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/hex/claude-council/bug-fixer"><img src="https://agentmods.dev/badge/skills/hex/claude-council/bug-fixer.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 | $0.00025 | $0.00931 |
| Opus 5.5 | $0.00010 | $0.00372 |
| Sonnet 5.5 | $0.00005 | $0.00186 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
bug-fixer 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 18d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fixer
Fix one reported bug at its root cause, with proof that the fix works. The change must be as small as it can be. Every claim in your report must rest on something you ran.
Before you change anything
- Restate the bug in one sentence: what the user does, what happens, what should happen. If the task does not say what should happen, and neither a spec, the docs, nor an existing test settles it, stop and report the ambiguity instead of choosing.
- Read the project's own instructions (AGENTS.md, CONTRIBUTING, README) for how to build and run tests.
- Reproduce the failure. Prefer the real user path: the command, request or UI action from the report. Record the exact command and the output that shows the bug. If it does not reproduce, stop and report what you tried and what you saw. Do not fix a bug you cannot see.
Find the cause
- Trace from the symptom to the code that makes the wrong decision. Read the owning function, its callers and callees, and any sibling implementation that does the same job correctly. Diff the two.
- State one hypothesis and test it with the smallest check that can prove it wrong: a log line, a debugger stop, a narrowed input. If it is wrong, go back and re-read; do not stack guesses.
- Distinguish cause from symptom. A null check where the value arrives is a symptom patch if the real fault is the code that should never have produced the null.
Make the fix
- Change the code that owns the decision, not a caller that happens to see the bad result.
- Keep the diff minimal. No refactors, renames, formatting sweeps or unrelated cleanups. Note them in the report instead.
- No fallback that hides the failure: no silent default, no swallowed exception, no retry that masks the cause. If the bad state is impossible after the fix, fail loudly if it appears anyway.
- Never weaken, skip or delete a test to get a pass. A failing test is information. If a test encodes the buggy behaviour as expected, say so in the report with the evidence, and change it only when the spec proves it wrong.
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.
- 18d ago First seen · 92 lines · 25 tokens per session scan A 3684c8c5686a
bug-fixer is a skill published in the GitHub repository hex/claude-council (872 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 931 once invoked, about $0.0001 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 2026-09-26.
Other skills, from other repositories
qa-expert
Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.
bugbash
Systematically explore and test any software project (CLI, API, Backend, Library, etc.) to find bugs, usability issues, and edge cases. Produces a structured report with full reproduction evidence (exact commands, inputs, logs, and tracebacks) for every issue.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
module-regression
Govern cross-module regression in large repositories with a REGRESSION.md ledger that records each module's downstream consumers and executable acceptance command. After a change, run the changed module and every affected downstream command, and use observed exit codes as regression evidence under the project's…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…