Agent skill

Surgical Patch

by JuliusBrussee in JuliusBrussee/caveman

“Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.”

— description from SKILL.md by JuliusBrussee
Apache-2.0Auto-check passedDevelopment

Install Surgical Patch

skills CLI
$ npx skills add JuliusBrussee/caveman --skill surgical-patch -a claude-code

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

GitHub CLI
$ gh skill install JuliusBrussee/caveman surgical-patch --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/JuliusBrussee/caveman.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/surgical-patch .claude/skills/surgical-patch && 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
surgical-patch
GitHub stars
110k
Used in
1 other repo
Token cost
~166 tokens
SKILL.md length
60 words
Files
2
Skills in repo
18
Repo updated
First seen
Licence
Apache-2.0

At a glance

  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

About this skill

Surgical Patch is a skill in JuliusBrussee/caveman (110k stars). Its SKILL.md is about 166 tokens, with 1 other file in the folder, and copies of it appear in 1 other owners' repositories. Licence: Apache-2.0.

What it can do on your machine

Read from SKILL.md and the folder at commit 538b491. 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

Surgical Patch loads about 166 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 60 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~166

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 JuliusBrussee/caveman at commit 538b491, republished under its Apache-2.0 licence (© JuliusBrussee). 60 words, ~166 tokens.

Download SKILL.mdSave it as .claude/skills/surgical-patch/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
surgical-patch
description
Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.

Surgical patch

Reproduce failure first when economical; otherwise capture strongest available evidence.

  • Trace symptom to responsible mechanism.
  • Change narrowest layer that owns incorrect behavior.
  • Preserve unrelated behavior and user changes.
  • Avoid cleanup, renaming, and abstraction outside fix.
  • Add only regression proof relevant to task.

Run focused proof plus nearest affected gate. Stop when failure is fixed and regression proof passes.

© JuliusBrussee, Apache-2.0. 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 1 other file in skills/surgical-patch of JuliusBrussee/caveman.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 538b491

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 JuliusBrussee/caveman, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Surgical Patch 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.

Surgical Patch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Surgical Patch this skillJuliusBrussee/caveman110k1 repos~166Automated safety check: PassApache-2.0
Vibe Coding PartnershareAI-lab/Kode-CLI5.2k—~5.6kAutomated safety check: PassApache-2.0
Odoo Workflowunclecatvn/agent-skills143—~4.7kAutomated safety check: PassMIT
Code Review21pounder/terminalAgent1201 repos~650Automated safety check: PassApache-2.0
Code WriterWildGums/Orc.LicenseManager108—~2.3kAutomated safety check: PassCustom licence
Find Bugsgetsentry/skills1k9 repos~708Automated safety check: PassApache-2.0

Similar skills

  • Vibe Coding Partner

    shareAI-lab/Kode-CLI

    Gives an agent a set of working rules for any development task: understand first, surface decisions, verify results, and load deeper reference files per scenario.

    5.2k GitHub stars~5.6k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Odoo Workflow

    unclecatvn/agent-skills

    Mandatory pre-code gate and definition-of-done for ANY Odoo change (add field, override method, inherit view/xpath, OWL/JS patch, wizard, cron, controller, report, security, migration, bug fix…

    143 GitHub stars~4.7k tokensUpdated 14 days ago
    DevelopmentAuto-check passed
  • Code Review

    21pounder/terminalAgent

    A skill your agent uses when user asks to "review code", "check for issues", "analyze code quality", "find bugs", or wants feedback on code implementation.

    120 GitHub starsUsed in 1 repo~650 tokens
    DevelopmentAuto-check passed
  • Code Writer

    WildGums/Orc.LicenseManager

    Write production C code following repository coding standards and architecture.

    108 GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Find Bugs

    getsentry/skills

    Official

    Find bugs, security vulnerabilities, and code quality issues in local branch changes.

    1k GitHub starsUsed in 9 repos~708 tokens
    DevelopmentAuto-check passed
  • Build Until Pass Loop

    LichAmnesia/lich-skills

    Drives a failing build, typecheck, lint or test command to a passing exit code through small, one-fix-at-a-time rounds, stopping at a hard attempt cap instead of looping forever.

    234 GitHub stars~2.8k tokensUpdated 4 mo ago
    DevelopmentAuto-check passed

More from JuliusBrussee/caveman

All 18 skills in this repo
  • Caveman Workflow Labeler

    JuliusBrussee/caveman

    Finds every LLM workflow in a repository, proposes a labeling table and, once you agree, wires labels so Caveman Cloud groups spend per workflow.

    110k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • Caveman Evidence Review

    JuliusBrussee/caveman

    Read-only review of Caveman Cloud data to explain where LLM spend goes: cost, score, workflows, traces, latency, errors, routing and verified savings.

    110k GitHub starsUsed in 1 repo~927 tokens
    Auto-check passed
  • Caveman Experiment Manager

    JuliusBrussee/caveman

    Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself.

    110k GitHub starsUsed in 1 repo~975 tokens
    Auto-check passed
  • Caveman Optimization Evaluator

    JuliusBrussee/caveman

    Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.

    110k GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • Caveman Gateway Setup

    JuliusBrussee/caveman

    Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.

    110k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check: warnings
  • Caveman Help Card

    JuliusBrussee/caveman

    Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".

    110k GitHub stars~690 tokensUpdated today
    Auto-check passed

Categories

Questions about Surgical Patch

How do I install Surgical Patch in Claude Code?

Run `npx skills add JuliusBrussee/caveman --skill surgical-patch -a claude-code`. Or copy the skill folder (skills/surgical-patch in JuliusBrussee/caveman) into .claude/skills/surgical-patch in your project. Claude Code loads it when a task matches its description.

How do I install Surgical Patch in Codex?

Run `npx skills add JuliusBrussee/caveman --skill surgical-patch -a codex`. Or copy the skill folder (skills/surgical-patch in JuliusBrussee/caveman) into .agents/skills/surgical-patch in your project. Codex loads it when a task matches its description.

Can I use Surgical Patch 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 JuliusBrussee/caveman --skill surgical-patch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/surgical-patch, .gemini/skills/surgical-patch, .github/skills/surgical-patch and .opencode/skills/surgical-patch in your project.

What does Surgical Patch need to run?

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

Does Surgical Patch 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 Surgical Patch 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 Surgical Patch use?

Surgical Patch is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Surgical Patch use?

About 166 tokens (SKILL.md is roughly 664 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 Surgical Patch?

Skills that share tags, products or a category with Surgical Patch: Vibe Coding Partner (shareAI-lab/Kode-CLI, 5.2k stars), Odoo Workflow (unclecatvn/agent-skills, 143 stars), Code Review (21pounder/terminalAgent, 120 stars) and Code Writer (WildGums/Orc.LicenseManager, 108 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Surgical Patch?

JuliusBrussee (a GitHub user) maintains it in JuliusBrussee/caveman, which has 110,443 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 8, 2026.

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