commit

A command template for creating a Git commit message from staged changes and GitHub issue details.

In plain words
What is it for?
Use it to write a subject like a feature, bug fix, or chore message after reviewing the staged diff.
Why use it?
It keeps messages within the required Conventional Commits format and validation rules without making the commit itself.

Command for Claude Code

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/jayminwest/kotadb/commit
Clone the repo
git clone --depth 1 https://github.com/jayminwest/kotadb

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 1,114 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 $0.00000 $0.01114
Opus 5 $0.00000 $0.00557
Sonnet 5 $0.00000 $0.00223
Haiku 4.5 $0.00000 $0.00111

Measured yesterday against content hash 928b003166c1, 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/git/commit.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/commit

Template Category: Message-Only

Generate a git commit message for the staged work.

Variables

  • agent_name: $1 (planner or implementor)
  • issue_type: $2 (feature, bug, chore)
  • issue_json: $3 (GitHub issue payload)

Instructions

  • Commit message format: <issue_type>: ${issue_number} - <short description>.
  • Description must be ≤ 60 characters, present tense, no trailing period.
  • Preface the body (if needed) with Generated with ADW ID: <adw_id> is handled elsewhere—only craft the subject.
  • Review git diff HEAD to understand staged changes before generating the message.
  • DO NOT execute git commands (staging/committing is handled by the orchestration layer).

CRITICAL: Commit Message Validation Rules

Your commit message will be validated by automation/adws/adw_modules/validation.py. It MUST pass these checks:

Format Requirements

  • Conventional Commits format: <type>(<scope>): <subject>
  • Valid types: feat, fix, chore, docs, test, refactor, perf, ci, build, style
  • Subject length: 1-72 characters (keep under 60 for best practices)
  • Optional scope: You can add a scope in parentheses after the type (e.g., feat(api):)

Meta-Commentary Patterns (FORBIDDEN in first line)

DO NOT include these phrases anywhere in the commit message subject line:

  • based on
  • the commit should
  • here is
  • this commit
  • i can see
  • looking at
  • the changes
  • let me

These patterns indicate agent reasoning leakage. The commit message should be a direct statement, not a description of your thought process.

Examples

✅ CORRECT (these will pass validation):

chore: 98 - document test path resolution strategy
feat: 123 - add rate limiting middleware
fix: 456 - resolve API key validation bug
docs: 789 - update authentication guide

❌ INCORRECT (these will FAIL validation):

Based on the changes, I can see this is a documentation update
The commit should be: chore - update docs
Here is the commit message for the changes
This commit documents the test path resolution strategy
Looking at the diff, the changes add rate limiting

Read the full file on GitHub · 129 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. yesterday First seen · 129 lines · 0 tokens per session scan A 928b003166c1

Subscribe to this mod's changes

commit is a command published in the GitHub repository jayminwest/kotadb (102 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,114 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.