Agent skill

Targeted Emergency Bug Fix

by VeryGoodOpenSource in VeryGoodOpenSource/vgv-wingspan

Applies a minimal fix to an emergency bug through triage, root-cause location, a hotfix branch and a blast-radius check, with tests and review still required.

MITAuto-check passedDevelopment

Install Targeted Emergency Bug Fix

skills CLI
$ npx skills add VeryGoodOpenSource/vgv-wingspan --skill hotfix -a claude-code

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

GitHub CLI
$ gh skill install VeryGoodOpenSource/vgv-wingspan hotfix --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/VeryGoodOpenSource/vgv-wingspan.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hotfix .claude/skills/hotfix && 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
hotfix
GitHub stars
108
Token cost
~1.9k tokens
SKILL.md length
1,003 words
Files
7 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Applies a minimal fix to an emergency bug through triage, root-cause location, a hotfix branch and a blast-radius check, with tests and review still required.

  • Works in 6 steps: Triage → Locate → Branch → …
  • Shipping a small, targeted fix for a production bug without a full planning cycle
  • SKILL.md covers Bug Description, Phase 0 — Triage, Phase 1 — Locate and Phase 2 — Branch, plus 5 more sections
  • Calls git

What it does

This workflow skips brainstorm and plan documents but keeps tests and review mandatory. It needs a bug description, whether a symptom, an issue link or an error message, and asks for one if it is missing. The agent triages the bug in one sentence with symptom and suspected area, then uses a codebase-review agent to locate the responsible code narrowly and summarizes the root cause in two to three sentences, asking you for more context if the cause stays unclear.

It proposes a `hotfix/` branch named from the bug description unless you are already on one, then runs a blast-radius check before any code is written. If the fix would touch more than five files, several layers or new abstractions, it warns you and offers to switch to planning. Changes must be minimal with no drive-by refactors, and out-of-scope issues get a TODO(hotfix) comment. Reference files cover driving the build to green, a PR template, review agent instructions, consolidating review findings and a review report template. The only shell command it declares permission for is removing `docs/hotfix-review/`.

When your agent uses it

  • Shipping a small, targeted fix for a production bug without a full planning cycle
  • Keeping an urgent fix to a minimal, reviewed and tested change
  • Deciding whether an urgent bug is contained enough to skip planning

Example prompts

  • “Hotfix: checkout throws a null error when the cart has no shipping address.”
  • “Fix the login redirect loop from the latest bug report as an emergency.”
  • “Triage this stack trace and apply the smallest safe fix on a hotfix branch.”

Requirements

  • A git repository
  • An agent environment that supports subagents, such as Claude Code
  • Compatibility (from SKILL.md): Designed for Claude Code (or similar products with agent support)
  • Pre-approved tools (allowed-tools): Bash(rm -rf docs/hotfix-review/)

Workflow steps

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

  1. Triage
  2. Locate
  3. Branch
  4. Fix
  5. Review
  6. Ship

What it can do on your machine

Read from SKILL.md and the folder at commit 19e0695. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(rm -rf docs/hotfix-review/)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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.

  • Compatibility

    Designed for Claude Code (or similar products with agent support)

    From compatibility in the SKILL.md frontmatter.

Context cost

Targeted Emergency Bug Fix loads about 1.9k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 1,003 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

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 VeryGoodOpenSource/vgv-wingspan at commit 19e0695, republished under its MIT licence (© VeryGoodOpenSource). 1,003 words, ~1,919 tokens.

Download SKILL.mdSave it as .claude/skills/hotfix/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
hotfix
description
Applies a minimal, targeted fix for emergency bugs — enforces review and testing without brainstorm or planning phases.
allowed-tools
Bash(rm -rf docs/hotfix-review/)
compatibility
Designed for Claude Code (or similar products with agent support)
user-invocable
true
effort
high
argument-hint
bug description, issue link, or error message

Hotfix — emergency fix workflow

Apply a minimal, targeted fix fast. No brainstorm document, no plan document — but tests and review are still non-negotiable.

Bug Description

<bug_description>$ARGUMENTS</bug_description>

If the bug description above is empty, ask the user: "What's the bug? Paste a description, issue link, or error message."

DO NOT proceed until you have a bug description.

Phase 0 — Triage

Summarize the bug in one sentence. Identify:

  • Symptom: what the user sees or what is broken
  • Suspected area: which layer or component is likely involved (based on the description alone — do not read code yet)

Phase 1 — Locate

Run a focused codebase exploration to find the problem area:

  • Task @codebase-review-agent("Locate the code responsible for this bug. Focus narrowly on the symptom described — do not survey the entire codebase. Bug: <bug_description>")

After the agent returns:

  1. Read the identified files and their immediate neighbors to understand the context.
  2. Identify the root cause (or the most likely candidate).
  3. Summarize the root cause to the user in 2-3 sentences.

If the root cause is unclear after exploration, use AskUserQuestion to ask the user for additional context before proceeding.

Phase 2 — Branch

Set up a hotfix branch. Unlike normal feature branches, hotfix branches use the hotfix/ prefix.

Run:

bash
git rev-parse --abbrev-ref HEAD

If already on a hotfix/ branch: skip silently.

Otherwise: infer a branch name in the format hotfix/<kebab-slug> where the slug is derived from the bug description (max 60 characters total). Use AskUserQuestion to confirm:

  1. Create branch (Recommended) — git checkout -b hotfix/<slug>
  2. Skip — stay on the current branch

Phase 3 — Fix

Blast Radius Check

Before writing any code, outline which files and layers the fix touches.

If >5 files, multiple layers, or new abstractions needed: warn the user and use AskUserQuestion: (1) Proceed with hotfix, (2) Switch to /plan.

If contained (≤5 files, single layer): proceed directly.

Step 1: Implement

Write the minimal change that addresses the root cause. Change only what is necessary — no drive-by refactors. If you touch unrelated code, stop and flag scope creep. Leave // TODO(hotfix): <description> comments for out-of-scope issues. Match surrounding code style.

Step 2: Test

Tests are non-negotiable, even for hotfixes:

  • Add or update tests that reproduce the bug (the test should fail without the fix).
  • Cover the fix path and any closely related edge cases.
  • Do not write tests for unrelated code.
Step 3: Validate

Follow the validation and fix procedure.

Execution Rules
  • Never skip tests. Every fix gets a regression test.
  • Never add features not related to the bug (YAGNI).
  • If the fix grows beyond the original scope, stop and flag it.
  • Acceptable tradeoffs: a hotfix may intentionally introduce a lesser issue (e.g., fixing a P0 while accepting a P2 side effect). When this happens, document the tradeoff clearly with a // TODO(hotfix): <description of known limitation and its severity> comment in the code and note it in the PR description. The goal is to stop the bleeding, not achieve perfection.
  • Ask the user only when genuinely stuck: ambiguous root cause, 3 failed fix attempts, or a missing dependency.

Phase 4 — Review

Run review agents in parallel to validate the fix. Use a reduced set — speed matters, but quality is non-negotiable.

Agent instructions

Run pwd and let <PWD> be the result — subagents may change directories, making relative paths unreliable.

Each agent prompt must include the review agent instructions with <RAW_DIR> set to <PWD>/docs/hotfix-review/raw and <name> set to the agent's report name below (a bare stem — the agent writes <RAW_DIR>/<name>.md). Substitute <PWD> with the absolute path.

The reduced agent set and their report names (<name>):

AgentReport name
@vgv-review-agentvgv-review
@test-quality-review-agenttest-quality-review

If an agent fails, note it, continue with the other, and record the failure in the report header so the reduced review isn't silently halved.

Show full SKILL.md (384 more words)Show less
After reviews complete

Follow the review consolidation procedure: deduplicate the agents' structured findings, order them deterministically, assign stable FINDING-NN ids, and write one consolidated file to <PWD>/docs/hotfix-review/review.md using the report template. Print the aligned chat summary (same ids, order, and titles as the file). Then fix Critical findings by id and present Important findings to the user. The report is deleted at Cleanup, so the fix commit does not cite FINDING-NN ids.

Cleanup

Remove review reports after findings are addressed:

bash
rm -rf docs/hotfix-review/

Phase 5 — Ship

Drive to green

A hotfix has no plan, so there is no success-criteria block. Follow the drive to green procedure with the detected project suite (formatter, linter, test runner) as both the gate set and the authoritative command run once. It loops until green by real output, delegates to a matching installed verification skill when one exists, and escalates only on un-runnable or self-contradictory failures — never on an ordinary, fixable one. Do not proceed until it is green.

Ship

Create a single, cherry-pick-friendly commit. Stage only fix-related files (no unrelated changes). Use this commit format:

text
fix: <concise description of what was fixed>

<Root cause explanation in 1-2 sentences>

Bug: <original bug description or issue link, truncated if long>

Push the branch and create a PR. Title: fix: <concise description> (under 70 chars). Body: Use the PR template.

Post-Ship

Use AskUserQuestion to present options:

  1. Done: end the session

Gotchas

  • If the bug is in a shared dependency or utility, the fix may affect callers you did not expect. Grep for all usages before changing shared code.
  • If the fix requires a migration (database, config, schema), this is likely too large for a hotfix. Recommend switching to /plan → /build.
  • Hotfix branches use the hotfix/ prefix, not fix/. Other skills use fix/ — do not mix them.
  • If docs/hotfix-review/ already exists from a previous interrupted hotfix, delete it before running Phase 4 to avoid stale reports contaminating the review.
  • The blast radius check (Phase 3) uses a threshold of 5 files. A fix that touches exactly 5 files is within threshold; 6 triggers the warning.

Important

  • This skill is for emergency fixes. It trades planning depth for speed, but never trades away quality.
  • No brainstorm or plan documents are generated.
  • Tests and review are non-negotiable — fast doesn't mean sloppy.
  • Keep the diff minimal. A hotfix that grows into a feature rewrite belongs in /plan → /build.
  • The commit must be cherry-pick-friendly: one commit, one concern, no unrelated changes.

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

Files

SKILL.md and 6 other files (references) in skills/hotfix of VeryGoodOpenSource/vgv-wingspan.

  • SKILL.md
  • references/drive-to-green.md
  • references/pr-template.md
  • references/review-agent-instructions.md
  • references/review-consolidation.md
  • references/review-report-template.md
  • references/validate-and-fix.md

Open the folder on GitHubat commit 19e0695

Compare with similar skills

Targeted Emergency 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.

Targeted Emergency Bug Fix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Targeted Emergency Bug Fix this skillVeryGoodOpenSource/vgv-wingspan108—~1.9kAutomated safety check: PassMIT
Git History Bug Auditben-manes/caffeine18k—~3.3kAutomated safety check: PassApache-2.0
Codexqa Rootcause Analyzeropenqa-cn/codexqa152—~2.6kAutomated safety check: PassApache-2.0
TiDB Test Diff Triagepingcap/tidb41k—~498Automated safety check: PassApache-2.0
Code Design Rationale Investigatorcursor/plugins10k9 repos~2.6kAutomated safety check: PassNone
Debugging and Error Recoveryaddyosmani/agent-skills102k1 repos~2.6kAutomated safety check: PassMIT

Similar skills

  • Git History Bug Audit

    ben-manes/caffeine

    Audits a module by walking its git history commit by commit, tracking unresolved issues forward, and reporting the ones that survive to HEAD as findings.

    18k GitHub stars~3.3k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis.

    152 GitHub stars~2.6k tokensUpdated 5 days ago
    DevelopmentAuto-check passed
  • Investigates TiDB plan or test-result diffs that the change does not explain, ruling out failpoint setup and merge effects before expected outputs are updated.

    41k GitHub stars~498 tokensUpdated today
    Testing & QAAuto-check passed
  • Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Debugging and Error Recovery

    addyosmani/agent-skills

    Applies a stop-the-line rule and a step-by-step triage when tests fail, builds break or something stops working, aiming at the root cause instead of guesses.

    102k GitHub starsUsed in 1 repo~2.6k tokens
    DevelopmentAuto-check passed
  • Addresses unresolved pull request review threads and suppressed (low-confidence) Copilot review comments on the current branch, folds each fix into the…

    1.8k GitHub stars~657 tokensUpdated 6 days ago
    DevelopmentAuto-check passed

More from VeryGoodOpenSource/vgv-wingspan

All 11 skills in this repo
  • On-Demand Code Review

    VeryGoodOpenSource/vgv-wingspan

    Runs parallel review agents over a branch, chosen paths or a whole project and merges their findings into one numbered report you can act on by id.

    108 GitHub stars~1.7k tokensUpdated 7 days ago
    Auto-check passed
  • Git Rebase onto Base Branch

    VeryGoodOpenSource/vgv-wingspan

    Rebases the current feature branch onto the latest main, master or develop, stashing uncommitted work first and aborting cleanly if conflicts appear.

    108 GitHub stars~786 tokensUpdated 7 days ago
    Auto-check passed
  • Feature Brainstorm

    VeryGoodOpenSource/vgv-wingspan

    Clarifies what to build before how, by asking one question at a time about a feature idea and then handing the result on to planning.

    108 GitHub stars~1.8k tokensUpdated 7 days ago
    Auto-check passed
  • Create Pull Request

    VeryGoodOpenSource/vgv-wingspan

    Stages, commits, pushes and opens a pull request with a Conventional Commits message, after running the project's checks unless told to skip them.

    108 GitHub stars~1.3k tokensUpdated 7 days ago
    Auto-check: notes
  • Post-Incident Debrief

    VeryGoodOpenSource/vgv-wingspan

    Produces a blameless post-incident debrief with timeline, root cause and follow-up actions after an outage, failed release or significant bug, while details are fresh.

    108 GitHub stars~1.9k tokensUpdated 7 days ago
    Auto-check passed
  • Plan

    VeryGoodOpenSource/vgv-wingspan

    Turns high-level brainstorming and ideas into well-structured, actionable implementation plans.

    108 GitHub stars~2.8k tokensUpdated 7 days ago
    Auto-check passed

Works with

Questions about Targeted Emergency Bug Fix

What does Targeted Emergency Bug Fix do?

Applies a minimal fix to an emergency bug through triage, root-cause location, a hotfix branch and a blast-radius check, with tests and review still required. This workflow skips brainstorm and plan documents but keeps tests and review mandatory. It needs a bug description, whether a symptom, an issue link or an error message, and asks for one if it is missing.

When should I use Targeted Emergency Bug Fix?

Targeted Emergency Bug Fix fits situations like: shipping a small, targeted fix for a production bug without a full planning cycle; keeping an urgent fix to a minimal, reviewed and tested change; deciding whether an urgent bug is contained enough to skip planning.

How do I install Targeted Emergency Bug Fix in Claude Code?

Run `npx skills add VeryGoodOpenSource/vgv-wingspan --skill hotfix -a claude-code`. Or copy the skill folder (skills/hotfix in VeryGoodOpenSource/vgv-wingspan) into .claude/skills/hotfix in your project. Claude Code loads it when a task matches its description.

How do I install Targeted Emergency Bug Fix in Codex?

Run `npx skills add VeryGoodOpenSource/vgv-wingspan --skill hotfix -a codex`. Or copy the skill folder (skills/hotfix in VeryGoodOpenSource/vgv-wingspan) into .agents/skills/hotfix in your project. Codex loads it when a task matches its description.

Can I use Targeted Emergency 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 VeryGoodOpenSource/vgv-wingspan --skill hotfix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hotfix, .gemini/skills/hotfix, .github/skills/hotfix and .opencode/skills/hotfix in your project.

What does Targeted Emergency Bug Fix need to run?

Going by SKILL.md and its folder, Targeted Emergency Bug Fix needs the command-line tools its instructions call (git). Our summary lists: A git repository; An agent environment that supports subagents, such as Claude Code. Its frontmatter pre-approves these tools: Bash(rm -rf docs/hotfix-review/). Compatibility (from SKILL.md): Designed for Claude Code (or similar products with agent support).

Does Targeted Emergency Bug Fix access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Targeted Emergency 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 Targeted Emergency Bug Fix use?

Targeted Emergency 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 Targeted Emergency Bug Fix use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 145 tokens, read only when the agent opens those files.

What are the alternatives to Targeted Emergency Bug Fix?

Skills that share tags, products or a category with Targeted Emergency Bug Fix: Git History Bug Audit (ben-manes/caffeine, 18k stars), Codexqa Rootcause Analyzer (openqa-cn/codexqa, 152 stars), TiDB Test Diff Triage (pingcap/tidb, 41k stars) and Code Design Rationale Investigator (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Targeted Emergency Bug Fix?

VeryGoodOpenSource (a GitHub organization) maintains it in VeryGoodOpenSource/vgv-wingspan, which has 108 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 30, 2026.

Source: VeryGoodOpenSource/vgv-wingspan on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.