Fix bugs with regression prevention using test-first approach

MITAuto-check passedDevelopment

Install Bug Fix

skills CLI
$ npx skills add undeadlist/claude-code-agents --skill bug-fix -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install undeadlist/claude-code-agents bug-fix --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/undeadlist/claude-code-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/bug-fix .claude/skills/bug-fix && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
bug-fix
GitHub stars
149
Token cost
~307 tokens
SKILL.md length
128 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Fix bugs with regression prevention using test-first approach

  • Works in 4 steps: Reproduce with Test → Fix the Bug → Verify → …
  • Tasks that involve Debugging
  • SKILL.md covers Execution (Sequential), Usage and Skip browser-qa for
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Bug Fix is an agent skill from undeadlist/claude-code-agents. Fix bugs with regression prevention using test-first approach

Its SKILL.md is about 310 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Debugging and Test-driven development. The repository describes itself as: Claude Code Agents Prompt templates for Claude Code's subagent system. Run parallel code audits, automate fix cycles, get stuff reviewed. Built for the Claude Code Task tool. Not… The licence is MIT.

When your agent uses it

  • Tasks that involve Debugging
  • Tasks that involve Test-driven development

Example prompts

  • “/bug-fix”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Reproduce with Test
  2. Fix the Bug
  3. Verify
  4. Browser QA (if UI bug)

What it can do on your machine

Read from SKILL.md and the folder at commit 13e3d51. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bug Fix loads about 307 tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 128 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~307

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from undeadlist/claude-code-agents at commit 13e3d51, republished under its MIT licence (© undeadlist). 128 words, ~307 tokens.

Download SKILL.mdSave it as .claude/skills/bug-fix/SKILL.md (or your agent's skills folder).
name
bug-fix
description
Fix bugs with regression prevention using test-first approach

Bug Fix Workflow

Fix bugs with a test-first approach to prevent regressions. Provide the bug description when invoking.

Execution (Sequential)

Step 1: Reproduce with Test

Spawn test-writer with the bug description:

  • Create a test that fails (reproduces the bug)
  • Test should pass after the fix is applied
Step 2: Fix the Bug

Spawn code-fixer with the bug description and test file:

  • Find root cause
  • Implement minimal fix
  • Don't refactor unrelated code
Step 3: Verify

Spawn test-runner:

  • New test passes (bug is fixed)
  • All existing tests pass (no regressions)
Step 4: Browser QA (if UI bug)

Spawn browser-qa-agent:

  • Reproduce original steps
  • Confirm bug is fixed
  • Check related features still work

Usage

Provide bug details when invoking:

/bug-fix

Bug: Login fails with valid credentials
Steps to reproduce:
1. Go to /login
2. Enter valid email/password
3. Click submit
Expected: Redirect to dashboard
Actual: 500 error
Location: src/api/auth/login.ts

Skip browser-qa for

  • Non-UI bugs (API, background jobs)
  • Build/compilation issues
  • Test infrastructure bugs

© undeadlist, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/bug-fix of undeadlist/claude-code-agents.

Open the folder on GitHubat commit 13e3d51

Compare with similar skills

Bug Fix next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bug Fix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bug Fix this skillundeadlist/claude-code-agents149—~307Automated safety check: PassMIT
Compound Engineering DebugEveryInc/compound-engineering-plugin25k—~4.2kAutomated safety check: PassMIT
Development Workflowrunceel/ReactiveProperty944—~1.4kAutomated safety check: PassMIT
Debugging Difficult Bugsmastra-ai/mastra29k—~1.9kAutomated safety check: PassCustom licence
Golang Troubleshootingsamber/cc-skills-golang3.4k—~3.3kAutomated safety check: PassMIT
Systematic Debuggingtmdgusya/engineering-discipline125—~2kAutomated safety check: PassNone

Similar skills

  • Compound Engineering Debug

    EveryInc/compound-engineering-plugin

    Finds the root cause of failing or slow behavior with a hypothesis-driven loop, then fixes it test-first if you choose, or hands back a diagnosis only.

    25k GitHub stars~4.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Development Workflow

    runceel/ReactiveProperty

    ReactiveProperty repository development policy. An agent skill from runceel/ReactiveProperty.

    944 GitHub stars~1.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Debugging Difficult Bugs

    mastra-ai/mastra

    Use early when debugging a medium or hard bug, especially when tests alone may not reveal the real runtime failure.

    29k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Golang Troubleshooting

    samber/cc-skills-golang

    Troubleshoot Golang programs systematically - find and fix the root cause.

    3.4k GitHub stars~3.3k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Systematic Debugging

    tmdgusya/engineering-discipline

    A skill your agent uses when encountering any bug, test failure, or unexpected behavior.

    125 GitHub stars~2k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Hexagonal Architecture

    citypaul/.dotfiles

    A skill your agent uses when the user or project explicitly adopts hexagonal (ports and adapters) architecture — a README, CLAUDE.md, or ADR that says so is the opt-in.

    739 GitHub stars~10k tokensUpdated 5 days ago
    DevelopmentAuto-check passed

More from undeadlist/claude-code-agents

  • Full Audit

    undeadlist/claude-code-agents

    Run all 11 audit agents in parallel, then consolidate findings with fix-planner

    149 GitHub stars~445 tokensUpdated 3 mo ago
    Auto-check passed
  • New Feature

    undeadlist/claude-code-agents

    Develop new features with test-first approach (TDD). An agent skill from undeadlist/claude-code-agents.

    149 GitHub stars~295 tokensUpdated 3 mo ago
    Auto-check passed
  • Pre Commit

    undeadlist/claude-code-agents

    Run code quality checks and tests before committing. An agent skill from undeadlist/claude-code-agents.

    149 GitHub stars~220 tokensUpdated 3 mo ago
    Auto-check passed
  • Pre Deploy

    undeadlist/claude-code-agents

    Validate build, environment, and dependencies before deployment

    149 GitHub stars~291 tokensUpdated 3 mo ago
    Auto-check passed
  • Release Prep

    undeadlist/claude-code-agents

    Full audit + fixes + deploy validation for production release

    149 GitHub stars~357 tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Bug Fix

What does Bug Fix do?

Fix bugs with regression prevention using test-first approach. Bug Fix is an agent skill from undeadlist/claude-code-agents.

When should I use Bug Fix?

Bug Fix fits situations like: tasks that involve Debugging; tasks that involve Test-driven development.

How do I install Bug Fix in Claude Code?

Run `npx skills add undeadlist/claude-code-agents --skill bug-fix -a claude-code`. Or copy the skill folder (skills/bug-fix in undeadlist/claude-code-agents) into .claude/skills/bug-fix in your project. Claude Code loads it when a task matches its description.

How do I install Bug Fix in Codex?

Run `npx skills add undeadlist/claude-code-agents --skill bug-fix -a codex`. Or copy the skill folder (skills/bug-fix in undeadlist/claude-code-agents) into .agents/skills/bug-fix in your project. Codex loads it when a task matches its description.

Can I use Bug Fix in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add undeadlist/claude-code-agents --skill bug-fix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bug-fix, .gemini/skills/bug-fix, .github/skills/bug-fix and .opencode/skills/bug-fix in your project.

What does Bug Fix need to run?

SKILL.md names no scripts, command-line tools or credentials: Bug Fix is instructions for the agent only.

Does Bug Fix access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bug Fix safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Bug Fix use?

Bug Fix is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bug Fix use?

About 307 tokens (SKILL.md is roughly 1.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Bug Fix?

Skills that share tags, products or a category with Bug Fix: Compound Engineering Debug (EveryInc/compound-engineering-plugin, 25k stars), Development Workflow (runceel/ReactiveProperty, 944 stars), Debugging Difficult Bugs (mastra-ai/mastra, 29k stars) and Golang Troubleshooting (samber/cc-skills-golang, 3.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bug Fix?

undeadlist (a GitHub user) maintains it in undeadlist/claude-code-agents, which has 149 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on June 28, 2026.

Source: undeadlist/claude-code-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.