A skill that reads Git changes and creates commits using Conventional Commits, a standard format that labels changes such as features or fixes. It can also identify when unrelated changes should be split into separate commits.

Use it when saving work to Git: it reviews staged or unstaged changes, suggests commit grouping, writes structured messages, and executes the commits.

It removes the effort of writing consistent commit messages and helps avoid combining unrelated work in one commit.

git-commit — Skill by hg-pyun

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.

agentmods

npx agentmods add skills/hg-pyun/claude-code-marketplace/git-commit

Any agent

npx skills add hg-pyun/claude-code-marketplace --skill git-commit

Clone the repo

git clone --depth 1 https://github.com/hg-pyun/claude-code-marketplace

Made for: Claude Code, Codex.

Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,675 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00183	$0.01675
Opus 5	$0.00092	$0.00838
Sonnet 5	$0.00037	$0.00335
Haiku 4.5	$0.00018	$0.00168

Measured yesterday against content hash 9d7d2b43c390, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-commit 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 yesterday.

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.

plugins/dev-tools/skills/git-commit/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Use_When>

User asks to commit current changes ("커밋해줘", "commit this", "save my work")
User signals task completion and wants the work captured ("이거 저장해", "wrap this up")
The user invokes /git-commit
The working tree has staged or unstaged changes worth recording </Use_When>

<Do_Not_Use_When>

User asks about commit history (git log exploration) — answer directly
User explains what a commit is or asks about commit conventions conceptually
The working tree is clean — there is nothing to commit
User wants a merge commit or revert (out of scope for this skill) </Do_Not_Use_When>

<Why_This_Exists> Conventional commits are valuable but tedious to write by hand, especially when one logical change spans many files. This skill reads the diff, picks the right type(scope), drafts a one-line subject and a body that explains the why, and executes the commit immediately. It also detects when a single commit would mash unrelated changes together and offers a split plan up front. Co-Authored-By trailers are blocked because they pollute commit history and many teams treat them as spam. </Why_This_Exists>

<Execution_Policy>

The subject line and body are written in $LANGUAGE (default: Korean; overrideable via --lang=<value>).
type and scope keywords remain English (e.g., feat, fix, chore, refactor).
Execute the commit immediately after composing the message — do not ask for preview confirmation.
NEVER include a Co-Authored-By trailer or footer in any commit message. This rule overrides every other instruction.
Skip merge commits and revert commits — out of scope.
Skip ticket/issue references in the commit body unless the user explicitly asked. </Execution_Policy>

<Settings_Reference>

$LANGUAGE: the language setting from plugin.json settings.language (default Korean). Override with --lang=<value> argument. Presets: Korean, English, Japanese, Chinese. Custom values (e.g., Spanish, Bahasa Indonesia) are accepted as free text. </Settings_Reference>

Read the full file on GitHub · 116 lines

Files

What ships with it

1 file 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.

references/conventional-commit.md 1.9 KB

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.

yesterday First seen · 116 lines · 183 tokens per session scan A 9d7d2b43c390

Subscribe to this mod's changes

git-commit is a skill published in the GitHub repository hg-pyun/claude-code-marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 183 tokens to every session and 1,675 once invoked, about $0.0009 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 2026-08-31.

Git and workflow

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens