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 thixpin/pitway --skill bug-fixgit clone --depth 1 https://github.com/thixpin/pitwayWrote 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/thixpin/pitway/bug-fix)<a href="https://agentmods.dev/skills/thixpin/pitway/bug-fix"><img src="https://agentmods.dev/badge/skills/thixpin/pitway/bug-fix/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/thixpin/pitway/bug-fix"><img src="https://agentmods.dev/badge/skills/thixpin/pitway/bug-fix.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 | $0.00052 | $0.00578 |
| Opus 5.5 | $0.00021 | $0.00231 |
| Sonnet 5.5 | $0.00010 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
bug-fix 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 1mo 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fix
Fix bugs regression-first: prove the bug exists, fix the cause minimally, prove it cannot return.
Scope
Use for any defect with observably wrong behavior and a known cause — crashes, incorrect output, regressions.
This skill begins once the root cause is identified. If the cause is still unknown, use debugging first, then return here with it.
Do not use for:
- Writing or restructuring tests against working code — use
testing. - Improving healthy code that has no defect — use
code-quality-review.
A vulnerability is a bug: use this workflow and the security-audit checklist together.
Workflow
- Reproduce first. Confirm the bug with a concrete failing case — a command, request, or input that demonstrably misbehaves. If you cannot reproduce it, use
debuggingto establish a reliable trigger before continuing here. - Confirm the root cause. State it in one sentence before fixing, and check the fix targets it rather than the symptom (no null check where the real problem is that the value should never be null). If tracing from symptom to cause is still open work, finish that in
debuggingfirst. - Write the regression test before the fix whenever the project has a test suite and the bug is testable. The test must fail on the current code for the same reason the bug occurs. If an automated test is infeasible (environment-dependent, UI-only, timing), state why and describe the manual verification used instead.
- Fix minimally. The smallest change that removes the root cause. No drive-by refactoring, renames, or style changes in the same edit — propose those separately if worthwhile.
- Verify. Run the regression test, then the smallest relevant surrounding test suite to catch collateral damage.
- Check for siblings. Search for other call sites or copies of the same pattern that share the defect. Fix or report them — a bug that exists in three places and is fixed in one is still open.
Judgment calls
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.
- 1mo ago First seen · 36 lines · 52 tokens per session scan A d2c632a6353c
bug-fix is a skill published in the GitHub repository thixpin/pitway (20 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 578 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
pair-programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
systematic-debugging
Structured root-cause debugging loop — reproduce, isolate, form a hypothesis, verify the fix. Use whenever a bug, crash, test failure, or unexpected behavior is reported.
tdd
This skill should be used when the user asks to "add a feature using TDD", "fix a bug with TDD", "do TDD", "red-green-refactor", "write a failing test first", "use test-driven development", "start TDD", "test first approach", "TDD loop", "TDD cycle", or mentions TDD workflow, baby steps, guessing game, or…
fix-issue
Fix a GitHub issue following project coding standards. Creates branch, implements fix with TDD, and prepares PR.
leader-triage-investigate-resolve
Orchestrate the full lifecycle of delegated problem resolution: triage severity and blast radius, drive hypothesis-based investigation through team members, then coordinate the fix with regression testing and verification. This pipeline composes leaf skills (triage-methodology, scientific-debugging) into a leader…
systematic-debugging
Reproduce failures, isolate root cause with evidence, and fix them through a regression test.