A Git command that reviews changes and creates a commit using the conventional commit format, such as `fix(scope): description`. It can also create a feature branch when committing from the main branch.

Use it to inspect staged changes, choose a concise commit type and scope, create a branch when needed, and commit the work.

It helps produce consistent commit messages and reduces the risk of committing feature work directly to the main branch.

commit — Command by TheDecipherist

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/thedecipherist/claude-code-mastery-project-starter-kit/commit

Clone the repo

git clone --depth 1 https://github.com/TheDecipherist/claude-code-mastery-project-starter-kit

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 527 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	$0.00009	$0.00527
Opus 5	$0.00005	$0.00264
Sonnet 5	$0.00002	$0.00105
Haiku 4.5	$0.00001	$0.00053

Measured 2d ago against content hash 5addd67edf76, 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.

.claude/commands/commit.md · 62 lines

What it actually says

Smart Commit

Context

Current git status: !git status --short
Current diff: !git diff HEAD --stat
Current branch: !git branch --show-current
Recent commits: !git log --oneline -5

Auto-Branch (if on main)

Before committing, check the current branch:

git branch --show-current

Default behavior (auto_branch = true in claude-mastery-project.conf):

If on main or master: automatically create a feature branch from the staged changes context:
```
git checkout -b feat/<scope-from-changes>
```
Report: "Created branch feat/<scope> — committing there instead of main." Then proceed with the commit on the new branch.
If already on a feature branch: proceed normally
If not a git repo: skip this check

To disable: Set auto_branch = false in claude-mastery-project.conf. When disabled, warn and ask the user to confirm before committing to main.

Task

Review the staged changes and create a commit.

Rules

Use conventional commit format: type(scope): description
- Types: feat, fix, docs, style, refactor, test, chore, perf
Description should be concise but descriptive (max 72 chars)
If changes span multiple concerns, suggest splitting into multiple commits
NEVER commit .env files or secrets
Verify .gitignore includes .env before committing

If message provided

Use this as the commit message: $ARGUMENTS

If no message provided

Generate an appropriate commit message based on the diff.

RuleCatch Report (post-commit)

After the commit succeeds, check RuleCatch for violations in the committed files:

If the RuleCatch MCP server is available: query for violations on the files in this commit
Report: "RuleCatch: X violations found in committed files" (with details if any)
If no MCP available: remind the user — "Check your RuleCatch dashboard for violations in this commit"
If violations are found: DO NOT undo the commit, just report them so the user can decide

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.

2d ago First seen · 62 lines · 9 tokens per session scan A 5addd67edf76

Subscribe to this mod's changes

commit is a command published in the GitHub repository TheDecipherist/claude-code-mastery-project-starter-kit (337 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 527 once invoked, about $0.0000 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.

Commits Git and workflow

commit

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Smart Commit

Context

Auto-Branch (if on main)

Task

Rules

If message provided

If no message provided

RuleCatch Report (post-commit)

What this file has done since we first saw it

Other commands, from other repositories

speckit.git.commit

commit

commit-all

commit

commit

commit