A Git workflow command that creates Conventional Commits by examining staged changes, recent commit style, and the current branch. It can enforce GitHub Flow, where work is developed on separate branches and merged through review.

Use it to detect the commit type and scope, create or select a feature branch when needed, commit the staged work, and continue through pull-request and release steps.

It removes much of the guesswork from writing commits and helps keep protected branches from receiving direct changes. Security checks and pull-request steps are included in the broader flow.

commit — Command for Claude Code by fusengine/agents

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.

Clone the repo

git clone --depth 1 https://github.com/fusengine/agents

Made for: Claude Code.

Or install fuse-commit-pro, the plugin that ships this one along with the rest of its 4 skills, 10 commands, 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/commands/fusengine/agents/commit/github.svg)](https://agentmods.dev/commands/fusengine/agents/commit)

Your own site

<a href="https://agentmods.dev/commands/fusengine/agents/commit"><img src="https://agentmods.dev/badge/commands/fusengine/agents/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/commands/fusengine/agents/commit"><img src="https://agentmods.dev/badge/commands/fusengine/agents/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,477 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	$0.00031	$0.03477
Opus 5.5	$0.00012	$0.01391
Sonnet 5.5	$0.00006	$0.00695
Haiku 4.5	$0.00003	$0.00348

Measured 7d ago against content hash 9b4291998d03, 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 7d 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.

plugins/commit-pro/commands/commit.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Conventional Commit

Current State

!git status

Staged Changes

!git diff --staged --stat

Recent Commits (style reference)

!git log --oneline -5

Current Branch

!git branch --show-current

Instructions

Based on the context above, create a professional commit.

Step 0: Branch Check (GitHub Flow enforcement)

Read current branch from above.

If current branch is main, master, develop, or production:

BLOCK direct commits and propose a feature branch:

🌿 Branch Protection
───────────────────────────────
Current: <branch>
Issue: Direct commits to protected branches discouraged (GitHub Flow)
───────────────────────────────

Pre-detect commit type/scope from staged changes (Step 2 logic) to suggest branch name:
  - feat(seo) → feat/seo
  - fix(sniper) → fix/sniper
  - chore(deps) → chore/deps

Proposed branch: <type>/<scope-or-summary>

Options:
  Y → Create branch + continue commit
  N → Abort
  C → Custom branch name

If user accepts → execute git checkout -b <branch> then proceed to Step 1. If user declines → STOP, do not commit.

If current branch already a feature branch (e.g. feat/*, fix/*, chore/*, docs/*, refactor/*, perf/*, test/*, ci/*, build/*, style/*) → skip to Step 1 directly.

Exceptions (allow direct commit on main):

Repo has only main branch and no remote (solo prototype)
User explicitly passes --no-branch-check in $ARGUMENTS
Commit type is chore AND scope is release or version (post-commit bump commits)

Step 1: Security Check

BLOCK and output if secrets detected:

🔒 Security Alert
───────────────────────────────
Found: [file or pattern]
Action: Commit blocked
Fix: Remove sensitive data before committing

Check for:

.env, .env.* files
Patterns: password=, secret=, api_key=, token=
Files: *.pem, *.key, *credentials*

Step 2: Analyze and Detect

Output analysis:

📊 Analysis
───────────────────────────────
Files changed: [X]
Files staged: [Y]
Pattern detected: [type]

Read the full file on GitHub · 297 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.

7d ago Changed · +26 lines 9b4291998d03
22d ago Changed a8bded1a9c6a
1mo ago First seen · 271 lines · 31 tokens per session scan A 19f6bd3c637a

Subscribe to this mod's changes

commit is a command published in the GitHub repository fusengine/agents (33 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 3,477 once invoked, about $0.0001 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 2026-09-03.

Claude Code Commits Git and workflow Releases Security claude-agent claude-agents claude-code-plugin claude-skills claudecode

flow

Universal workflow entry point. Use /flow for skill-driven GitHub development. Verbs: start, commit, pr, review, address, merge, resolve, release, status, learn, setup, explain, debug, design, brainstorm, issue.

synaptiai/synapti-marketplace · 56 tokens

close-track

Close a completed track — run quality gate, update conductor state, commit, and optionally handle the git branch.

Ibrahim-3d/orchestrator-supaconductor · 24 tokens

nyann:ship

Open a GitHub pull request AND merge it in one step. Default uses GitHub's native auto-merge (returns immediately with outcome:"queued"); --client-side polls for green CI in the foreground then runs gh pr merge. Requires gh installed + authed.

thettwe/nyann · 63 tokens

nyann:hotfix

Create the branch topology for a patch release against a previously tagged version. Ensures release/ . exists from the source tag, then creates hotfix/ off it. After this, the user commits the fix and runs /nyann:release from the hotfix branch.

thettwe/nyann · 69 tokens

nyann:commit

Generate a Conventional Commits message from the staged diff and commit after confirmation. Same flow as the natural-language commit skill — dispatches here so users who prefer explicit slash commands can bypass intent detection.

thettwe/nyann · 46 tokens

ship

Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…

PrabhdeepSingh/claude-plugins · 86 tokens