What is lov-gh-contribute?

A workflow for contributing changes to someone else’s GitHub repository by creating a fork, making branches, and opening a pull request.

Use it when you need to fork a repository, prepare existing changes, commit and push them, and submit one or more pull requests on GitHub.

It provides the steps for sending code upstream when you do not have permission to write directly to the original repository, including separating unrelated changes.

lov-gh-contribute — Skill for Claude Code by lovstudio

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.

Any agent

npx skills add lovstudio/skills --skill gh-contribute

Clone the repo

git clone --depth 1 https://github.com/lovstudio/skills

Made for: Claude Code.

Or install dev-tools, the plugin that ships this one along with the rest of its 31 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lovstudio/skills/gh-contribute.svg)](https://agentmods.dev/skills/lovstudio/skills/gh-contribute)

Your own site

<a href="https://agentmods.dev/skills/lovstudio/skills/gh-contribute"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/gh-contribute.svg" alt="Measured on agentmods" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,210 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 41
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00102	$0.02210
Opus 5	$0.00051	$0.01105
Sonnet 5	$0.00020	$0.00442
Haiku 4.5	$0.00010	$0.00221

Measured today against content hash 19e6f3e9f1c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

lov-gh-contribute 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 today.

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.

skills/gh-contribute/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

开源贡献助手 · Open Source Contributor

Turn local changes into a clean, professional pull request against an upstream repo you don't own. Handles the full fork → branch → commit → push → PR pipeline, and splits work into multiple PRs when the changes span unrelated concerns.

When to Use

User wants to contribute to an open-source project they don't have write access to
User already has local edits and needs them shipped as a PR upstream
User asks to "fork this repo and send a PR"
User has mixed changes (e.g. docs + feature + refactor) and wants them split properly

Non-Goals

Does not write code changes — assumes the user (or a prior step) already has the desired modifications in the working tree or in their head
Does not review the project's own PRs (see gh-tidy)
Does not mirror to GitLab/Gitea — GitHub only

Workflow (MANDATORY)

Execute steps in order. Do not skip confirmations.

Step 1: Identify the target repo

Determine the upstream owner/repo:

If the user pasted a URL or owner/repo string → use it
Otherwise run git remote -v in the current directory and pick the origin (if origin is already the user's fork, find the upstream via gh repo view --json parent)

Record three facts:

UPSTREAM — e.g. ZenMux/zenmux-doc
DEFAULT_BRANCH — from gh repo view $UPSTREAM --json defaultBranchRef -q .defaultBranchRef.name
USER_LOGIN — from gh api user -q .login

Step 2: Read the contribution rules

Fetch CONTRIBUTING.md and CODE_OF_CONDUCT.md from upstream (if present) and skim for: commit message format, DCO/CLA requirements, branch naming, PR template. Carry these constraints into subsequent steps.

gh api repos/$UPSTREAM/contents/CONTRIBUTING.md -q .content 2>/dev/null | base64 -d

If the repo has .github/PULL_REQUEST_TEMPLATE.md, use it as the PR body skeleton.

Step 3: Survey the changes

Gather the change set that needs to become PR(s):

git status --porcelain
git diff --stat $DEFAULT_BRANCH...HEAD        # committed
git diff --stat                                # unstaged
git diff --stat --cached                       # staged

Read the full file on GitHub · 251 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

today Changed 19e6f3e9f1c2
8d ago First seen · 251 lines · 102 tokens per session scan A 372046e7b105

Subscribe to this mod's changes

lov-gh-contribute is a skill published in the GitHub repository lovstudio/skills (64 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 2,210 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 2026-08-30.

Claude Code Git and workflow agent-skills ai-coding-assistant cjk cursor gemini-cli

lov-gh-contribute

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

开源贡献助手 · Open Source Contributor

When to Use

Non-Goals

Workflow (MANDATORY)

Step 1: Identify the target repo

Step 2: Read the contribution rules

Step 3: Survey the changes

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

create-pr

commit-staged

resolve-pr-comments

review-pr

update-pr-summary

clean-gone-branches