bugfix

bugfix is a skill for Claude Code, Codex from grimoire-rs/grimoire. It costs 92 tokens per session (1,535 once invoked), scanned A, original, Apache-2.0.

A bug-fixing workflow assistant that requires reproducing a problem, finding its cause, and writing a failing regression test before changing the code.

In plain words
What is it for?
Use it for bugs, crashes, incorrect output, and regressions, following the sequence from reproduction through fix, verification, review, and commit.
Why use it?
It prevents speculative fixes and confirms that the test can detect the reported failure.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/grimoire-rs/grimoire/bugfix
Any agent
npx skills add grimoire-rs/grimoire --skill bugfix
Clone the repo
git clone --depth 1 https://github.com/grimoire-rs/grimoire

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for bugfix

README.md
[![agentmods](https://agentmods.dev/badge/skills/grimoire-rs/grimoire/bugfix.svg)](https://agentmods.dev/skills/grimoire-rs/grimoire/bugfix)
Your own site
<a href="https://agentmods.dev/skills/grimoire-rs/grimoire/bugfix"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/bugfix.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,535 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00092 $0.01535
Opus 5 $0.00046 $0.00767
Sonnet 5 $0.00018 $0.00307
Haiku 4.5 $0.00009 $0.00153

Measured 3d ago against content hash 20942bc18c96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bugfix 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 3d 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.

.claude/skills/bugfix/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bugfix — Guided Bug-Fix Workflow

Guard rail for the #1 bug-fix failure: fixing before a failing test exists. This skill walks workflow-bugfix.md (the single source of truth) and adds one hard, non-skippable gate — Phase 3 must produce a test that fails on the current code before any fix is written.

Why this exists: the rule alone was repeatedly skipped. This skill makes the order explicit and the gate blocking. Read workflow-bugfix.md for the full rationale; this file is the executable checklist.

The non-negotiable sequence

Reproduce → Root-Cause Analysis → FAILING TEST → Fix → Verify → Review → Commit

Each phase finishes before the next starts. The only way past Phase 3 is a test that you have run and watched fail for the right reason.

Phase 1 — Reproduce (no guessing)

  • State the exact wrong behavior: command, input, observed vs expected.
  • Find the surface: which entry point(s)? CLI command, TUI path, library seam? A bug often lives on more than one surface (e.g. a CLI path AND its TUI twin); list every one that shares the broken code.
  • Confirm it actually reproduces. If you can't reproduce it, keep digging — no speculative fixes.

Write a one-line repro: "<cmd/inputs> → <observed>; expected <expected>".

Phase 2 — Root-Cause Analysis (write it down)

  • Trace the symptom to the line and the condition that made it fire.

  • Output a root-cause statement in this exact shape — no "error on line N":

    X happens because Y, introduced by/located at Z.

  • Single bug or a pattern? Grep for the same defect elsewhere (sibling call sites, the other surface from Phase 1). If it's a pattern, the fix covers all instances.

  • If the real cause needs an architectural change, stop and escalate to the feature workflow with a plan artifact — don't paper over it.

Phase 3 — Failing test FIRST 🚧 GATE

Do not edit any production code until this phase is done.

Read the full file on GitHub · 127 lines

Changes

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.

  1. 3d ago First seen · 127 lines · 92 tokens per session scan A 20942bc18c96

Subscribe to this mod's changes

bugfix is a skill published in the GitHub repository grimoire-rs/grimoire (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,535 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens