generate-commit-message

A Git commit-message drafting workflow for OneDev, a platform for hosting code repositories and pull requests. It reads the applicable message rules and describes the current changes.

In plain words
What is it for?
Use it to draft a compliant commit message for staged or unstaged changes in a OneDev repository.
Why use it?
It reduces the risk of proposing a commit message that violates branch or pull-request requirements.

Skill for Claude CodeCodex

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 skills/theonedev/tod/generate-commit-message
Any agent
npx skills add theonedev/tod --skill generate-commit-message
Clone the repo
git clone --depth 1 https://github.com/theonedev/tod

Made for: Claude Code, Codex.

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 636 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 $0.00064 $0.00636
Opus 5 $0.00032 $0.00318
Sonnet 5 $0.00013 $0.00127
Haiku 4.5 $0.00006 $0.00064

Measured 2d ago against content hash 7082ab5464df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate-commit-message 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.

skills/generate-commit-message/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate a OneDev commit message

Compose a commit message for the current change using requirements reported by OneDev.

Prerequisites

  • tod is installed and configured.
  • The current OneDev repository contains staged or unstaged changes to describe.

Pull request context

When the commit belongs to an existing or planned pull request, fetch both the branch and pull request requirements. The message must satisfy every non-empty requirement.

Workflow

  1. Read the commit-message requirements.

    Get the current branch requirement:

    tod get-commit-message-requirement
    

    In pull request context, also get the PR requirement:

    tod pr get-commit-message-requirement --target-project <target-project> --target-branch <target-branch> 
    

    For an existing PR, use values from its detail. For a planned PR, use the values or omissions planned for tod pr create.

    Empty output from either requirement command means no requirement from that source. When both are empty, fall back to a sensible default (short imperative subject, blank line, then body).

  2. Inspect the change. Use git to see exactly what will be committed so the message accurately describes it:

    git status
    git diff --cached         # staged changes
    git diff                  # unstaged changes (only if nothing is staged)
    
  3. Build the subject. Derive a concise imperative subject from the diff in step 2. Focus on the dominant change, not every touched file, and mention the affected component when it makes the change easier to scan in git log. Keep the subject short (~50 chars) unless a requirement from step 1 says otherwise.

  4. Write the body. Add a blank line after the subject, then explain why the change was made and any non-obvious trade-offs, impact, or follow-ups. Wrap lines at ~72 chars. Skip the body only for trivial commits where the subject is fully self-describing.

Read the full file on GitHub · 73 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 · 73 lines · 64 tokens per session scan A 7082ab5464df

Subscribe to this mod's changes

generate-commit-message is a skill published in the GitHub repository theonedev/tod (13 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 636 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.