New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Minimal Code Fix

by cobusgreyling in cobusgreyling/loop-engineering

Makes the smallest code change that fixes one well-scoped problem, such as a CI failure, review comment or typo, without refactoring anything unrelated.

MITAuto-check: notesDevelopment

Install Minimal Code Fix

skills CLI
$ npx skills add cobusgreyling/loop-engineering --skill minimal-fix -a claude-code

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

GitHub CLI
$ gh skill install cobusgreyling/loop-engineering minimal-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/cobusgreyling/loop-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/minimal-fix .claude/skills/minimal-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
minimal-fix
GitHub stars
11k
Used in
1 other repo
Token cost
~345 tokens
SKILL.md length
130 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Makes the smallest code change that fixes one well-scoped problem, such as a CI failure, review comment or typo, without refactoring anything unrelated.

  • Works in 5 steps: Reproduce or confirm the failure locally… → Identify the minimal root cause — not… → Change only what is required. No… → …
  • Fixing a specific CI failure that comes with an exact error message
  • SKILL.md covers Inputs, Process, Output and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill keeps the agent to a single specific problem and the smallest diff that could work. It takes an exact failure message, reviewer comment or issue description, the files involved if known, the project's build and test commands, and a path denylist from a loop safety policy that forbids editing .env, auth/, payments/ and secrets.

The process is to reproduce or confirm the failure, find the minimal root cause instead of symptoms in distant files, change only what is required, run the tests and lint relevant to the change, and summarize what changed, why and what was run. The output is a Minimal Fix Proposal. The rules say one problem per invocation, escalate when a denylist path is involved, prefer worktree isolation when a loop runs unattended, and leave it to the verifier to decide when work is done.

When your agent uses it

  • Fixing a specific CI failure that comes with an exact error message
  • Addressing a single reviewer comment without touching other code
  • Correcting a typo or another tightly scoped bug

Example prompts

  • “Fix the failing lint step in CI, where the error points to an unused import in utils/dates.ts, and change nothing else.”
  • “Address the reviewer comment about line handling in the CSV exporter with the smallest possible diff.”
  • “Fix the typo in the README install command and nothing else.”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Reproduce or confirm the failure locally if possible.
  2. Identify the minimal root cause — not symptoms in distant files.
  3. Change only what is required. No drive-by refactors.
  4. Run tests/lint relevant to the change.
  5. Summarize: what changed, why, what you ran.

What it can do on your machine

Read from SKILL.md and the folder at commit d25c2f4. 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 (its code samples are markdown).

    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

Minimal Code Fix loads about 345 tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 130 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~345

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:19
    t (from loop safety policy — never edit `.env`, `auth/`, `payments/`, secrets)

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 cobusgreyling/loop-engineering at commit d25c2f4, republished under its MIT licence (© cobusgreyling). 130 words, ~345 tokens.

Download SKILL.mdSave it as .claude/skills/minimal-fix/SKILL.md (or your agent's skills folder).
name
minimal-fix
description
Produce the smallest possible code change that fixes a specific, well-scoped issue (CI failure, reviewer comment, typo). Use only when the fix target is explicit. Never refactor unrelated code.
user_invocable
true

Minimal Fix Skill

You fix one specific problem with the smallest diff that could work.

Inputs

  • Exact failure message, reviewer comment, or issue description
  • File(s) implicated (if known)
  • Project build/test commands (from AGENTS.md or project skills)
  • Path denylist (from loop safety policy — never edit .env, auth/, payments/, secrets)

Process

  1. Reproduce or confirm the failure locally if possible.
  2. Identify the minimal root cause — not symptoms in distant files.
  3. Change only what is required. No drive-by refactors.
  4. Run tests/lint relevant to the change.
  5. Summarize: what changed, why, what you ran.

Output

markdown
## Minimal Fix Proposal

### Target
(one sentence)

### Diff summary
(files + what changed)

### Verification run
(command + result)

### Risks / human review needed?
(yes/no + why)

Rules

  • One problem per invocation. Multiple failures → escalate or triage first.
  • Respect denylist paths — escalate instead of editing.
  • Prefer worktree isolation when the loop runs unattended.
  • Do not mark your own work done — the verifier decides.

© cobusgreyling, 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/minimal-fix of cobusgreyling/loop-engineering.

Open the folder on GitHubat commit d25c2f4

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in cobusgreyling/loop-engineering, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Minimal Code 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.

Minimal Code Fix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Minimal Code Fix this skillcobusgreyling/loop-engineering11k1 repos~345Automated safety check: NotesMIT
Root Cause Debuggingjsmastery-pro/skills1.5k—~1.8kAutomated safety check: NotesMIT
Superpowers Systematic Debuggingchristopherarter/superpowers-reasonix102—~2kAutomated safety check: PassMIT
Failure Diagnosis LoopTotoro-jam/battle-tested-patterns345—~319Automated safety check: PassMIT
Hypothesis-Driven DebuggingLichAmnesia/lich-skills234—~2.5kAutomated safety check: PassMIT
Systematic Debuggingcbrock84/headcount2k—~657Automated safety check: PassMIT

Similar skills

  • Root Cause Debugging

    jsmastery-pro/skills

    Runs a reproduce, localize, hypothesize, test, fix and verify loop to find a bug's root cause, applies the minimal fix and hands off a regression test.

    1.5k GitHub stars~1.8k tokensUpdated 2 mo ago
    DevelopmentAuto-check: notes

  • Superpowers Systematic Debugging

    christopherarter/superpowers-reasonix

    Any bug, failing or flaky test, or surprise behavior?. An agent skill from christopherarter/superpowers-reasonix.

    102 GitHub stars~2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Failure Diagnosis Loop

    Totoro-jam/battle-tested-patterns

    Walks the agent through a fixed loop for failing tests and build errors: reproduce, isolate, hypothesize, instrument, fix, verify, then add a regression test.

    345 GitHub stars~319 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Hypothesis-Driven Debugging

    LichAmnesia/lich-skills

    Replaces trial-and-error fixing with an observe, hypothesize, experiment and conclude loop kept in DEBUG.md, where no fix is allowed before evidence supports a cause.

    234 GitHub stars~2.5k tokensUpdated 4 mo ago
    DevelopmentAuto-check passed

  • Systematic Debugging

    cbrock84/headcount

    Finds the root cause of a bug, test failure, or unexpected behavior before proposing any fix.

    2k GitHub stars~657 tokensUpdated 22 days ago
    DevelopmentAuto-check passed

  • Test Guided Bug Detector

    ArabelaTso/Skills-4-SE

    Analyze failing tests to detect functional bugs in code. An agent skill from ArabelaTso/Skills-4-SE.

    253 GitHub stars~2.8k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from cobusgreyling/loop-engineering

All 21 skills in this repo

  • Install Loop Engineering

    cobusgreyling/loop-engineering

    Installs Loop Engineering into a project through the single @cobusgreyling/loop CLI, scaffolding a report-only loop and a readiness score.

    11k GitHub starsUsed in 1 repo~648 tokens
    Auto-check passed

  • Loop Constraints Enforcer

    cobusgreyling/loop-engineering

    Loads a project's loop-constraints.md before any other action and blocks pushes, edits or merges that violate the rules it defines.

    11k GitHub starsUsed in 1 repo~475 tokens
    Auto-check: notes

  • Release Notes Drafter

    cobusgreyling/loop-engineering

    Turns a structured list of changes from changelog-scan into a categorized, user-facing release notes draft file, and never publishes anything.

    11k GitHub stars~555 tokensUpdated yesterday
    Auto-check passed

  • Issue Triage Loop

    cobusgreyling/loop-engineering

    Scans open GitHub issues and discussions, flags duplicates, scores priority and proposes labels into issue-triage-state.md without ever labeling or closing.

    11k GitHub stars~522 tokensUpdated yesterday
    Auto-check passed

  • Loop Triage Report

    cobusgreyling/loop-engineering

    Turns CI failures, open issues, recent commits and chat threads into a prioritized markdown report that an automation loop can act on without inventing architecture work.

    11k GitHub stars~500 tokensUpdated yesterday
    Auto-check passed

  • Loop Token Budget Guard

    cobusgreyling/loop-engineering

    Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.

    11k GitHub starsUsed in 1 repo~376 tokens
    Auto-check passed

Categories

Questions about Minimal Code Fix

What does Minimal Code Fix do?

Makes the smallest code change that fixes one well-scoped problem, such as a CI failure, review comment or typo, without refactoring anything unrelated. This skill keeps the agent to a single specific problem and the smallest diff that could work.env, auth/, payments/ and secrets.

When should I use Minimal Code Fix?

Minimal Code Fix fits situations like: fixing a specific CI failure that comes with an exact error message; addressing a single reviewer comment without touching other code; correcting a typo or another tightly scoped bug.

How do I install Minimal Code Fix in Claude Code?

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

How do I install Minimal Code Fix in Codex?

Run `npx skills add cobusgreyling/loop-engineering --skill minimal-fix -a codex`. Or copy the skill folder (skills/minimal-fix in cobusgreyling/loop-engineering) into .agents/skills/minimal-fix in your project. Codex loads it when a task matches its description.

Can I use Minimal Code 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 cobusgreyling/loop-engineering --skill minimal-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/minimal-fix, .gemini/skills/minimal-fix, .github/skills/minimal-fix and .opencode/skills/minimal-fix in your project.

What does Minimal Code Fix need to run?

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

Does Minimal Code 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 Minimal Code Fix safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Minimal Code Fix use?

Minimal Code 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 Minimal Code Fix use?

About 345 tokens (SKILL.md is roughly 1.4k 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 Minimal Code Fix?

Skills that share tags, products or a category with Minimal Code Fix: Root Cause Debugging (jsmastery-pro/skills, 1.5k stars), Superpowers Systematic Debugging (christopherarter/superpowers-reasonix, 102 stars), Failure Diagnosis Loop (Totoro-jam/battle-tested-patterns, 345 stars) and Hypothesis-Driven Debugging (LichAmnesia/lich-skills, 234 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Minimal Code Fix?

cobusgreyling (a GitHub user) maintains it in cobusgreyling/loop-engineering, which has 11,444 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 9, 2026.

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