A command that prepares Git commits, which are saved snapshots of changes in Git. It guides you to separate unrelated changes and write clear commit messages, with optional emojis called gitmoji.

Use it when finishing work to split changes into sensible commits and describe each change accurately.

It prevents vague commit history and makes it easier to understand, review, or undo changes later. Separating concerns also makes individual changes easier to find.

commit — Command by liam-hq

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/liam-hq/liam/commit

Clone the repo

git clone --depth 1 https://github.com/liam-hq/liam

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 931 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	$0.00000	$0.00931
Opus 5	$0.00000	$0.00465
Sonnet 5	$0.00000	$0.00186
Haiku 4.5	$0.00000	$0.00093

Measured yesterday against content hash 3de8a45e59f6, 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 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/commands/commit.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Let's commit the changes.

Split large changes: If changes touch multiple concerns, split them into separate commits Write a commit message that matches the content of your change: Clearly describe what was changed in this commit. A good commit message should:

Specify the component or feature affected (e.g., "authentication module").
Describe the action taken (e.g., "fixed a bug," "added a new feature").
Avoid vague messages like "fix bug" or "update code."

Examples of good commit messages:

🐛 Fixed a bug in the authentication module causing login failures
✨ Added a new feature to filter tables by column
📝 Updated README.md with new installation instructions

Examples of bad commit messages:

"fix bug"
"update code"
"changes made"
Use gitmoji (optional, recommended): Write commit messages using the emoji (e.g., ✨) itself, not the textual representation (e.g., :sparkles:)

Examples

✨ Added a new feature to filter tables
🐛 Fixed a typo in the welcome message
📝 Updated README.md with new installation instructions

Gitmoji Reference

Frequently Used

🚸 :children_crossing: - Improve user experience / usability
✨ :sparkles: - Introduce new features
🐛 :bug: - Fix a bug
♻️ :recycle: - Refactor code
⚡ :zap: - Improve performance
💄 :lipstick: - Add or update the UI and style files
🎨 :art: - Improve structure / format of the code
📝 :memo: - Add or update documentation
🔧 :wrench: - Add or update configuration files

Testing & Quality

✅ :white_check_mark: - Add, update, or pass tests
🚨 :rotating_light: - Fix compiler / linter warnings
🧪 :test_tube: - Add a failing test
🥅 :goal_net: - Catch errors

Critical Changes

🚑 :ambulance: - Critical hotfix
💥 :boom: - Introduce breaking changes
🔒 :lock: - Fix security or privacy issues

Dependencies & CI/CD

➕ :heavy_plus_sign: - Add a dependency
➖ :heavy_minus_sign: - Remove a dependency
⬆️ :arrow_up: - Upgrade dependencies
⬇️ :arrow_down: - Downgrade dependencies
💚 :green_heart: - Fix CI Build
👷 :construction_worker: - Add or update CI build system

Read the full file on GitHub · 88 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.

yesterday First seen · 88 lines · 0 tokens per session scan A 3de8a45e59f6

Subscribe to this mod's changes

commit is a command published in the GitHub repository liam-hq/liam (5,100 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 931 tokens. 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.

Databases Git and workflow Testing data-visualization database-schema documentation documentation-tool entity-relationship-diagram

commit

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Examples

Gitmoji Reference

Frequently Used

Testing & Quality

Critical Changes

Dependencies & CI/CD

What this file has done since we first saw it

Other commands, from other repositories

profile

ado-pull

archive

github-status

cancel-auto

doctor