amend-commit

A command for rewriting the message of the latest Git commit according to conventional commit conventions. It does not stage files, include uncommitted changes, push, or alter older commits.

In plain words
What is it for?
Inspecting the latest commit and amending its subject and body with an appropriate type, scope, and imperative description.
Why use it?
It improves an unclear or poorly structured commit description without changing the code or commit contents.

Command

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/krmcbride/claude-plugins/amend-commit
Clone the repo
git clone --depth 1 https://github.com/krmcbride/claude-plugins
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 935 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 $0.00016 $0.00935
Opus 5 $0.00008 $0.00467
Sonnet 5 $0.00003 $0.00187
Haiku 4.5 $0.00002 $0.00093

Measured yesterday against content hash f83e08a09535, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

amend-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.

essentials/commands/amend-commit.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Amend the last commit with a well-crafted message following conventional commit best practices.

User Input

$ARGUMENTS

Amend Commit Workflow

Step 1: Scope

This command ONLY amends the message of the last commit. It does NOT:

  • Add or stage any files
  • Include uncommitted changes
  • Push to remote
  • Modify any commits other than HEAD

Verify there is at least one commit by running git rev-parse HEAD.

Step 2: Gather Context

Run these commands to understand the commit:

# Current commit message
git log -1 --format=%B

# Commit statistics (files changed, insertions, deletions)
git show --stat HEAD

# Full diff for analysis
git show HEAD

Also note any type override or additional context from the user input above.

Step 3: Analyze and Draft New Message

Based on the diff, craft a new commit message following this format:

Subject Line (~72 chars)
type(scope): imperative description

Determine type from diff characteristics (user override takes precedence):

  • feat - New functionality, new files that add capabilities
  • fix - Bug fixes, error corrections
  • refactor - Code restructuring without changing behavior
  • docs - Documentation, README, comments
  • style - Formatting, whitespace, linting (no logic change)
  • test - Adding or updating tests
  • chore - Maintenance, dependencies, tooling
  • perf - Performance improvements
  • build - Build system, CI configuration
  • ci - CI/CD pipeline changes

Derive scope - use a short service, module, or feature name (not a file path):

  • Prefer domain concepts: auth, billing, search, api
  • Use feature names when appropriate: login, checkout, export
  • For libraries/packages: use the package name
  • If changes span multiple areas, use the most significant or omit scope entirely
  • Keep it short (ideally 3-10 chars) to leave room for the description

Write description in imperative mood:

  • "add user authentication" not "added user authentication"
  • "fix null pointer in parser" not "fixes null pointer"
  • No period at the end
  • Lowercase after the colon

Read the full file on GitHub · 164 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 · 164 lines · 16 tokens per session scan A f83e08a09535

Subscribe to this mod's changes

amend-commit is a command published in the GitHub repository krmcbride/claude-plugins (3 stars, last pushed 8mo ago), licensed MIT. It adds 16 tokens to every session and 935 once invoked, about $0.0001 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 2026-08-31.