wise-commit-message

A Git helper that reads staged and tracked, unstaged changes and drafts one Conventional Commit subject, such as a feature or bug-fix label followed by a short summary.

In plain words
What is it for?
Use it before committing to create a subject line from the changes currently visible to Git, with an optional clipboard copy.
Why use it?
It removes the guesswork from choosing a commit type, scope, and concise wording. It leaves the actual commit under your control.

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/e1024kb/wise-claude/wise-commit-message
Any agent
npx skills add e1024kb/wise-claude --skill wise-commit-message
Clone the repo
git clone --depth 1 https://github.com/e1024kb/wise-claude

Made for: Claude Code, Codex.

Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,585 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 $0.00195 $0.03585
Opus 5 $0.00097 $0.01792
Sonnet 5 $0.00039 $0.00717
Haiku 4.5 $0.00019 $0.00359

Measured 2d ago against content hash 422a29e75ba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wise-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.

plugins/wise/skills/wise-commit-message/SKILL.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wise-commit-message — draft a Conventional-Commits subject from pending changes

Why this skill exists

Every PR should land with a Conventional-Commits first line, and the "right" first line is mostly mechanical:

  1. Pick the type (feat / fix / refactor / docs / …) from what the diff actually does.
  2. Scope it with the Jira ticket the branch is working on — when there is one.
  3. Summarise the change in the imperative voice, short enough that the reader can scan a list of commits without hitting the wrap.

This skill automates the mechanical part. It looks at everything pending — both what's staged (git diff --cached) and what's modified-but-not-yet-staged in tracked files (git diff), but not the last commit and not untracked files — prints one line in Conventional-Commits form, and — with --copy — drops that line onto the clipboard so the user can paste it straight into git commit -m "…". When some of the described changes are not yet staged, the suggested commit command uses git add -A so the user doesn't end up committing only half of what the subject describes.

The user stays in control of the actual git commit call. Drafting and committing are intentionally separate here so the user can read the subject, tweak it, combine it with a body of their own, or reject it entirely without ever having created a commit object they'd need to amend.

Shared rules. §3–§5 below follow ${CLAUDE_PLUGIN_ROOT}/references/subject-drafting.md — the single source of truth that /wise-commit, /wise-commit-push, and draft-body.md also read. Change a Jira-detection, classification, or subject-formatting rule there, not here.

Invocation

/wise-commit-message
/wise-commit-message --copy
/wise:wise-commit-message          # canonical namespaced form
/wise:wise-commit-message --copy

No positionals. The only supported flag is --copy. Anything else the user types is treated as an error (see §Arguments).

Read the full file on GitHub · 358 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 · 358 lines · 195 tokens per session scan A 422a29e75ba2

Subscribe to this mod's changes

wise-commit-message is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 7d ago), licensed MIT. It adds 195 tokens to every session and 3,585 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

git-workflow-and-versioning

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…

addyosmani/agent-skills · 74 tokens

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

apm-issue-autopilot

Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…

microsoft/apm · 238 tokens

keploy-pr-workflow

Guide for creating PRs and issues on keploy repositories — PR format, customer-data hygiene, commit conventions, sign-off. Invoke when the user asks to open, update, or review a pull request or issue, when preparing a commit that will land in main, or whenever a change is about to leave the local machine.

keploy/keploy · 71 tokens

git-commit

Generate well-formatted git commit messages following conventional commit standards.

ThinkInAIXYZ/deepchat · 15 tokens

git-workflow

This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…

Galaxy-Dawn/claude-scholar · 64 tokens