amend

amend is a skill for Claude Code from drn/dots. It costs 37 tokens per session (569 once invoked), scanned A, original, MIT.

A skill that rewrites the message of the most recent Git commit after checking the commit's changes. Git is the version-control system used to record code changes.

In plain words
What is it for?
Use it to inspect the latest commit and amend its subject and optional body while following a concise, descriptive format.
Why use it?
It replaces vague or inaccurate last-commit messages with a description based on what actually changed.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to inspect the latest commit and amend its subject and optional body while following a concise, descriptive format.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/drn/dots/amend
View source ↗ drn/dots
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.

Any agent
npx skills add drn/dots --skill amend
Clone the repo
git clone --depth 1 https://github.com/drn/dots

Made for: Claude Code.

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.

agentmods badge for amend

README.md
[![agentmods](https://agentmods.dev/badge/skills/drn/dots/amend/github.svg)](https://agentmods.dev/skills/drn/dots/amend)
Your own site
<a href="https://agentmods.dev/skills/drn/dots/amend"><img src="https://agentmods.dev/badge/skills/drn/dots/amend/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.

agentmods 80×15 button for amend

Your own site · 80×15
<a href="https://agentmods.dev/skills/drn/dots/amend"><img src="https://agentmods.dev/badge/skills/drn/dots/amend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 569 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00037 $0.00569
Opus 5.5 $0.00015 $0.00228
Sonnet 5.5 $0.00007 $0.00114
Haiku 4.5 $0.00004 $0.00057

Measured 1mo ago against content hash 49d75689475d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

amend 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 1mo 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.

agents/skills/amend/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Amend Last Commit

Rewrite the last commit message with a clear, descriptive summary based on the actual changes.

Arguments

  • $ARGUMENTS - Optional: specific instructions for the commit message (e.g., "mention the performance improvement")

Context

  • Current branch: !git branch --show-current
  • Last commit: !git log -1 --format="%H %s" 2>/dev/null | head -1
  • Last commit body: !git log -1 --format="%b" 2>/dev/null | head -20
  • Diff stat: !git diff HEAD~1 --stat 2>/dev/null | head -30

Instructions

Step 1: Understand the changes

  1. Read the diff of the last commit: git diff HEAD~1 (full diff, not just stat)
  2. Read any files that were added or significantly changed to understand their purpose
  3. Check the current commit message — if it's already descriptive and accurate, tell the user and stop

Step 2: Draft the message

Write a commit message following this structure:

Subject line (first line):

  • Imperative mood ("Add", "Fix", "Update", not "Added", "Fixes")
  • Under 72 characters
  • Summarize WHAT changed and WHY at a high level
  • No trailing period

Body (separated by blank line, optional but preferred for non-trivial changes):

  • Explain what the change does and why it was made
  • Wrap lines at 72 characters
  • Focus on context that isn't obvious from the diff
  • Skip the body for truly trivial changes (typo fixes, version bumps)

Step 3: Amend the commit

Run git commit --amend with the new message. Use a HEREDOC to pass the message:

git commit --amend -m "$(cat <<'EOF'
Subject line here

Body paragraph here explaining the change in more detail.
EOF
)"

Step 4: Confirm

Show the user the new commit with git log -1 so they can verify.

Rules

  • Never change the commit contents — only the message. Do not stage or unstage files.
  • Preserve co-author trailers from the original message if present.
  • If the working tree has staged changes, warn the user that --amend will include them, and ask before proceeding.
  • If $ARGUMENTS contains specific instructions, incorporate them into the message.

Read the full file on GitHub · 68 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. 1mo ago First seen · 68 lines · 37 tokens per session scan A 49d75689475d

Subscribe to this mod's changes

amend is a skill published in the GitHub repository drn/dots (23 stars, last pushed 11d ago), licensed MIT. It adds 37 tokens to every session and 569 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 2026-08-30.