commit

A command set for examining Git changes and writing Conventional Commits messages, a standard format that labels changes such as features, fixes, tests, or documentation. It explains the reason for a change as well as its summary.

In plain words
What is it for?
Use it to review staged or unstaged differences, detect the change type and scope, identify breaking changes, stage related files, and produce a suitable commit message.
Why use it?
It removes guesswork when deciding how to describe a change and whether it may break users. It can also help organize related files and identify what should be staged.

Command

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 commands/nitinjain999/platform-skills/commit
Clone the repo
git clone --depth 1 https://github.com/nitinjain999/platform-skills
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,130 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.

ModelPer sessionOnce invoked
Fable 5 $0.00074 $0.01130
Opus 5 $0.00037 $0.00565
Sonnet 5 $0.00015 $0.00226
Haiku 4.5 $0.00007 $0.00113

Measured 2d ago against content hash 96a8a7fcbd9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

commands/commit.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:

  1. Run git diff --staged — if empty, run git diff HEAD to capture unstaged changes
  2. Group changed files by logical concern (feature, fix, refactor, docs, config, tests, ci)
  3. 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
  4. Infer scope from the most specific common ancestor: module name, service name, directory, or filename
  5. Check for breaking changes: API removals, signature changes, config renames, behavior inversions — flag with ! and add BREAKING CHANGE: footer
  6. 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:

  1. Run analyze mode first to determine type, scope, and breaking status
  2. 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"
  3. 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
  4. 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
  5. 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.

  1. 2d ago First seen · 106 lines · 74 tokens per session scan A 96a8a7fcbd9e

Subscribe to this mod's changes

commit is a command published in the GitHub repository nitinjain999/platform-skills (40 stars, last pushed 2d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,130 once invoked, about $0.0004 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.