eli-commit

eli-commit is a skill for Claude Code, Codex from kavyabhand/claude-eli5. It costs 59 tokens per session (433 once invoked), scanned A, original, MIT.

A tool that writes a Git commit message from the changes currently prepared for saving. It explains why the change was made, not just which files or lines changed.

In plain words
What is it for?
Use it to create a subject line and, when needed, a short explanation from staged changes. If no changes are staged, it can check the latest commit; if there is no usable diff, it asks what changed.
Why use it?
It helps turn a code diff into a short message that teammates can understand, even when they are new to the project.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create a subject line and, when needed, a short explanation from staged changes. If no changes are staged, it can check the latest commit; if there is no usable diff, it asks what changed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kavyabhand/claude-eli5/eli-commit
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 kavyabhand/claude-eli5 --skill eli-commit
Clone the repo
git clone --depth 1 https://github.com/kavyabhand/claude-eli5

Made for: Claude Code, Codex.

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 eli-commit

README.md
[![agentmods](https://agentmods.dev/badge/skills/kavyabhand/claude-eli5/eli-commit/github.svg)](https://agentmods.dev/skills/kavyabhand/claude-eli5/eli-commit)
Your own site
<a href="https://agentmods.dev/skills/kavyabhand/claude-eli5/eli-commit"><img src="https://agentmods.dev/badge/skills/kavyabhand/claude-eli5/eli-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.

agentmods 80×15 button for eli-commit

Your own site · 80×15
<a href="https://agentmods.dev/skills/kavyabhand/claude-eli5/eli-commit"><img src="https://agentmods.dev/badge/skills/kavyabhand/claude-eli5/eli-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 433 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00433
Opus 5.5 $0.00024 $0.00173
Sonnet 5.5 $0.00012 $0.00087
Haiku 4.5 $0.00006 $0.00043

Measured 1mo ago against content hash 3d1d5ee90ab4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eli-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 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.

skills/eli-commit/SKILL.md · 55 lines

What it actually says

ELI-COMMIT — Plain-Language Commit Message

Reads staged changes and writes a commit message that explains the why, not just the what.

Steps

1. Read staged changes

git diff --cached 2>/dev/null

If nothing staged, also try:

git diff HEAD~1..HEAD 2>/dev/null

2. Write the commit message

Subject line (required, ≤ 72 chars):

  • Starts with a verb: Add, Fix, Remove, Update, Simplify
  • Answers "what and why" in plain language
  • No jargon in the subject — if a technical term is unavoidable, follow with a plain equivalent

Body (optional, use when the why isn't obvious):

  • 2–4 bullet points
  • Focus on why this change was made, not what files changed (the diff shows that)
  • Plain language — a teammate who joined yesterday should understand

Rules

  • If the diff is empty, ask the user to describe the change
  • Use conventional commit format ONLY if the project already uses it (check existing commits)
  • Never summarize the diff literally ("changed line 42 of auth.js") — explain the reason
  • Short, clear subject line beats a long, jargon-heavy one every time

Example

Staged change: adds retry logic to API calls

Output:

Add automatic retry when the server is temporarily unavailable

- Without this, a single slow moment would fail the whole request for the user
- Now we try up to 3 times with a short pause between attempts
- No change to the user-facing experience — this is invisible when it works
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 · 55 lines · 59 tokens per session scan A 3d1d5ee90ab4

Subscribe to this mod's changes

eli-commit is a skill published in the GitHub repository kavyabhand/claude-eli5 (21 stars, last pushed 6mo ago), licensed MIT. It adds 59 tokens to every session and 433 once invoked, about $0.0002 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.