git-commit

A commit-message helper for a multi-module Maven project. Conventional commits are a standard format that labels changes, such as fixes, features, tests, or documentation.

In plain words
What is it for?
Use it when committing changes to generate messages with the correct type, module scope, subject, and optional explanation.
Why use it?
It removes guesswork when writing commit messages and helps keep module names and change types consistent.

Skill for Claude CodeCodex

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/adamw7/tools/git-commit
Any agent
npx skills add adamw7/tools --skill git-commit
Clone the repo
git clone --depth 1 https://github.com/adamw7/tools

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 696 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 $0.00046 $0.00696
Opus 5 $0.00023 $0.00348
Sonnet 5 $0.00009 $0.00139
Haiku 4.5 $0.00005 $0.00070

Measured yesterday against content hash b1bd4618e8e6, 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.

.claude/skills/git-commit/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Message Skill

Generate conventional, informative commit messages for the tools multi-module Maven reactor.

Format

Conventional Commits:

<type>(<scope>): <subject>

<body>

<footer>

Types

Type Use for
feat New API / functionality
fix Bug fix
refactor Restructure, no behavior change
test Add/update tests
docs Docs only (README, AGENTS.md, javadoc)
perf Performance improvement
build Maven / pom / CI changes
chore Maintenance (tooling, dependency bumps)

Scope — use this repo's real modules/components

data, code, context, protogen-maven-plugin, adopt, mcp-common, claude-code-enforcer, assembly, grpc-example, data-test. Narrow to a component when it's clearer (e.g. source.db, uniqueness, mcp, builder).

Subject rules

  • Imperative mood: "Add support", not "Added support"
  • Lowercase after the type, no trailing period, ≤ ~50 chars

Body (optional, recommended for non-trivial changes)

  • Explain what and why, not how; wrap at ~72 chars, 2–3 lines is plenty
  • Reference issues: Fixes #123 / Relates to #456
  • Breaking change: add a BREAKING CHANGE: footer (and ! after the scope)

Examples

feat(protogen-maven-plugin): enforce proto3 oneof discriminators at compile time

Generated builders now fail compilation when a required oneof branch is
left unset, matching the proto2 required-field guarantee.

Closes #123
fix(data): close JDBC statement when the result iterator is exhausted

IterativeDbSource leaked a Statement when callers stopped before the last
row. Wrap the cursor in try-with-resources so it closes on every path.

Fixes #456
refactor(context): extract project-tree assembly from the MCP adapter

Keeps the uniqueness/context core free of any MCP dependency, satisfying
the layering rule pinned by the architecture tests.
build(deps): add the shellcheck-maven-plugin with embedded binary resolution

Read the full file on GitHub · 89 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.

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. yesterday First seen · 89 lines · 46 tokens per session scan A b1bd4618e8e6

Subscribe to this mod's changes

git-commit is a skill published in the GitHub repository adamw7/tools (11 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 696 once invoked, about $0.0002 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.