A Git workflow that examines staged or unstaged changes and writes Conventional Commits messages. Conventional Commits is a shared format such as `feat`, `fix`, or `docs` that makes commit history easier to read and automate.

Use it to review a diff, classify its type and scope, detect breaking changes, stage logical groups of files, and create a commit message.

It turns a large or mixed diff into a short message that explains the reason for the change. It also flags likely breaking changes and can help stage related files.

commit — Skill for Claude Code by nitinjain999/platform-skills

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 nitinjain999/platform-skills --skill commit

Clone the repo

git clone --depth 1 https://github.com/nitinjain999/platform-skills

Made for: Claude Code.

Or install platform-skills, the plugin that ships this one along with the rest of its 50 skills, 1 agent.

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/nitinjain999/platform-skills/commit/github.svg)](https://agentmods.dev/skills/nitinjain999/platform-skills/commit)

Your own site

<a href="https://agentmods.dev/skills/nitinjain999/platform-skills/commit"><img src="https://agentmods.dev/badge/skills/nitinjain999/platform-skills/commit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nitinjain999/platform-skills/commit"><img src="https://agentmods.dev/badge/skills/nitinjain999/platform-skills/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,130 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.

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	$0.00074	$0.01130
Opus 5.5	$0.00030	$0.00452
Sonnet 5.5	$0.00015	$0.00226
Haiku 4.5	$0.00007	$0.00113

Measured 5d ago against content hash 96a8a7fcbd9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 5d ago.

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/commit/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze changes and generate a Conventional Commits message explaining the motivation behind the change.

Mode: analyze

Inspect staged or unstaged changes and classify the commit type and scope.

Steps:

Run git diff --staged — if empty, run git diff HEAD to capture unstaged changes
Group changed files by logical concern (feature, fix, refactor, docs, config, tests, ci)
Identify the type from the change pattern:
- feat — new capability or behavior added
- fix — corrects broken or incorrect behavior
- refactor — restructures code without changing behavior
- perf — measurably improves performance
- test — adds or corrects tests only
- docs — documentation only
- chore — build tooling, dependency updates, config changes with no production effect
- ci — changes to CI/CD pipelines or workflow files
- revert — reverting a prior commit
Infer scope from the most specific common ancestor: module name, service name, directory, or filename
Check for breaking changes: API removals, signature changes, config renames, behavior inversions — flag with ! and add BREAKING CHANGE: footer
Report: detected type, scope, whether breaking, and a one-line WHY summary

Reference: references/conventional-commits.md → Type Classification, Scope Rules

Mode: generate

Generate a complete conventional commit message from diff or description.

Steps:

Run analyze mode first to determine type, scope, and breaking status
Write the subject line:
- Format: <type>(<scope>): <imperative verb> <what and why>
- Max 72 characters
- Imperative mood: "add", "fix", "remove", "update", "extract" — not "added", "fixes"
- Focus on the WHY, not just the what: "fix(auth): validate token expiry before redirect" not "fix(auth): update token check"
Write the body (when the subject line is insufficient):
- Wrap at 72 characters
- Explain the problem being solved and the approach chosen
- One blank line between subject and body
Write footers:
- BREAKING CHANGE: <description> for breaking changes (also add ! to subject)
- Fixes #<issue> or Closes #<issue> for linked issues
- Co-authored-by: if applicable
Output the full message in a code block ready to copy

Read the full file on GitHub · 106 lines

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.

5d ago First seen · 106 lines · 74 tokens per session scan A 96a8a7fcbd9e

Subscribe to this mod's changes

commit is a skill published in the GitHub repository nitinjain999/platform-skills (70 stars, last pushed 3d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,130 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-12.

Commits DevOps and cloud Git and workflow ai-tools claude-code-plugin copilot-coding-agent grafana kubernetes

avi-pr-flow

Automate PR workflow with commit, push, create PR, and review cycle.

avi1234/claude-team-plugins · 15 tokens

create-pr-flow

Automate PR workflow with commit, push, create PR, and CI check.

avi1234/claude-team-plugins · 15 tokens

precommit

Pre-commit checks — lint:fix -> build -> test.

sd0xdev/sd0x-harness · 15 tokens

precommit-fast

Quick pre-commit checks — lint:fix -> test.

sd0xdev/sd0x-harness · 15 tokens

unslop-commit

Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…

MohamedAbdallah-14/unslop · 139 tokens

pre-commit-audit

Deliver a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode carriers. Use when the user requests a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode…

flonat/flonat-research · 100 tokens