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 nimadorostkar/Claude-Skills-collection --skill bug-fix-protocolgit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/bug-fix-protocol)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/bug-fix-protocol"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/bug-fix-protocol/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/nimadorostkar/claude-skills-collection/bug-fix-protocol"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/bug-fix-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00861 |
| Opus 5 | $0.00024 | $0.00430 |
| Sonnet 5 | $0.00010 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
bug-fix-protocol 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 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.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fix Protocol
Purpose
Turn a bug report into a merged fix without introducing a second bug. The protocol is deliberately rigid: it exists to prevent the two most common failures — fixing the symptom, and fixing the cause without proving it.
When to Use
- Any reported defect with a reproducible symptom.
- A regression discovered in CI or production.
- A hotfix under time pressure — especially then.
Capabilities
- Reproduction and minimization.
- Root-cause isolation (see the
debuggingskill for the search method). - Minimal, targeted fixes with regression tests.
- Blast-radius assessment for the same class of defect elsewhere.
Inputs
- The bug report: expected behavior, observed behavior, environment, steps.
- Access to logs, traces, or a failing build.
- The severity and whether a rollback is available.
Outputs
- A failing test that captures the bug.
- The smallest change that makes it pass.
- A note on where else this defect class could occur.
Workflow
- Reproduce before reading code. If you cannot reproduce it, the report is incomplete — go back for the missing detail. Do not guess.
- Write the failing test. In the real test suite, at the right level. It must fail for the right reason, with a clear message.
- Find the cause. Not the line where it crashed — the decision that made the crash possible.
- Fix minimally. Change only what is required. Refactoring belongs in a separate commit.
- Verify. New test passes; full suite passes; reproduce the original scenario manually and confirm it is gone.
- Look for siblings. Grep for the same pattern elsewhere. A bug found once is usually present three times.
- Close the loop. State in the PR: what broke, why, what changed, and what now prevents it.
Best Practices
- If you cannot write a test that fails before the fix, you have not understood the bug.
- Under time pressure, mitigate first (rollback, feature flag, rate limit), then fix properly. Do not ship a rushed fix to production and call it done.
- Never "fix" a flaky test by retrying it. Flakiness is a real defect in the test or the code.
- Do not widen a
try/exceptto make an error go away. That hides the next bug too. - Record the root cause in the issue, not just the fix. The next person will search for the symptom.
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 · 88 lines · 48 tokens per session scan A e6038d581718
bug-fix-protocol is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 23d ago), licensed MIT. It adds 48 tokens to every session and 861 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 skills, from other repositories
investigate
Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps. Use when the user asks to "investigate this bug", "debug this", "figure out why this fails", "find the root cause", "why is this broken"…
audit
Project-wide health audit pipeline that fans out to all analysis skills in parallel, evaluates findings, and produces a unified report at .turbo/audit.md. Use when the user asks to "audit the project", "run a full audit", "project health check", "audit my code", "codebase audit", or "comprehensive review".
consult-oracle
Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard problem, when standard approaches have failed, when multiple debugging attempts haven't worked, or when the user says "ask the oracle", "consult oracle", "consult chatgpt", "I'm completely…
find-dead-code
Find dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead. Use when the user asks to "find dead code", "find unused code", "find unused exports", "find unreferenced functions", "clean up dead code", or "what code is unused". Analysis-only — does not modify…
polish-code
Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".
simplify-code
Run a multi-agent review of changed files for scope, reuse, quality, efficiency, clarity, and altitude issues followed by fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes"…