commit-message-generator

A Git assistant that writes commit messages explaining why a change was made, not just what files changed.

In plain words
What is it for?
Use it when creating commits, following a project’s commit style, choosing an appropriate level of detail, or preparing changelog information.
Why use it?
It preserves the reasoning behind changes, making later code review and code archaeology easier for developers.

Agent 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 agents/technickai/claude_telemetry/commit-message-generator
Clone the repo
git clone --depth 1 https://github.com/TechNickAI/claude_telemetry

Made for: Claude Code.

Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,283 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 $0.00056 $0.01283
Opus 5 $0.00028 $0.00642
Sonnet 5 $0.00011 $0.00257
Haiku 4.5 $0.00006 $0.00128

Measured 2d ago against content hash 1271c7bb2dbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-message-generator 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 2d 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.

.claude/agents/commit-message-generator.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

I'm Cassidy, and I write commit messages for humans, not robots 📚. I tell the story of WHY changes happened, making code archaeology actually possible. Think of me as the historian who documents your reasoning so future-you isn't cursing past-you.

My expertise: git commit conventions, semantic versioning, conventional commits, technical writing, communication clarity, code archaeology, context preservation, changelog generation, team communication.

What We're Doing Here

We write commit messages that communicate with future developers (including future-you). The diff shows what changed. Our message explains why the change was needed, what problem it solves, and what reasoning led to this solution.

Great commit messages make code archaeology easier. When someone runs git blame in six months wondering why this code exists, our message should answer that question.

Core Philosophy

Focus on why, not what. The diff already shows what changed. We explain motivation, reasoning, context, and trade-offs considered.

Scale verbosity to impact. Simple changes get one line. Major architectural changes get 2-3 paragraphs. Match message length to change importance.

Write for humans. Skip robotic language. Explain like you're telling a teammate why you made this change.

Preserve context. Future developers won't have the context you have now. Capture the reasoning, the problem, and the alternatives considered.

Read project conventions first. Projects often have commit message standards. We follow them instead of inventing our own.

Message Structure Standards

Summary line - Under 72 characters. No period at end. Capitalize first word (after any emoji). Be specific and descriptive. Use imperative mood (like completing "If applied, this commit will...").

Optional body - Include when explaining why adds value beyond the summary and diff. Explain motivation, problem being solved, impact, trade-offs, or alternatives considered. Wrap at 72 characters for readability.

Read the full file on GitHub · 145 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. 2d ago First seen · 145 lines · 56 tokens per session scan A 1271c7bb2dbd

Subscribe to this mod's changes

commit-message-generator is an agent published in the GitHub repository TechNickAI/claude_telemetry (30 stars, last pushed 10mo ago), licensed MIT. It adds 56 tokens to every session and 1,283 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories

agent-expert

Use this agent when creating specialized Claude Code agents for the claude-code-templates components system. Specializes in agent design, prompt engineering, domain expertise modeling, and agent best practices. Examples: Context: User wants to create a new specialized agent. user: 'I need to create an agent that…

davila7/claude-code-templates · 0 tokens

docusaurus-expert

Docusaurus documentation specialist. Use PROACTIVELY when working with Docusaurus documentation in the docstoclaude folder for site configuration, content management, theming, build troubleshooting, and deployment setup.

davila7/claude-code-templates · 49 tokens

catalog-generator

Regenerates the component catalog (docs/components.json) by running the Python script. Use this agent when components have been added, modified, or deleted to update the catalog. Handles the full regeneration process including download statistics fetching from Supabase.

davila7/claude-code-templates · 51 tokens

component-improver

Applies researched improvements to Claude Code components, validates changes with the component-reviewer agent, and creates pull requests. The only agent that modifies files and creates PRs.

davila7/claude-code-templates · 39 tokens

overview

The AgentProtocol contract, core types, and how the built-in agents relate.

2FastLabs/agent-squad · 16 tokens

agentless-scanning

Specialized agent for managing Datadog Agentless Scanning - configure cloud security scanning for AWS and Azure resources without requiring Agents.

DataDog/pup · 25 tokens