commit-confirm

commit-confirm is a skill for Claude Code, Codex from LegendApp/legend-skills. It costs 81 tokens per session (395 once invoked), scanned A, original, MIT.

An approval step around the commit workflow in Git, the version-control system used to record code changes.

In plain words
What is it for?
Use it when you want to inspect all relevant working-tree changes, organize them into commits, approve the plan, and then commit them.
Why use it?
It prevents changes from being committed before you have reviewed and approved the proposed grouping and commit message.

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/legendapp/legend-skills/commit-confirm
Any agent
npx skills add LegendApp/legend-skills --skill commit-confirm
Clone the repo
git clone --depth 1 https://github.com/LegendApp/legend-skills

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 commit-confirm

README.md
[![agentmods](https://agentmods.dev/badge/skills/legendapp/legend-skills/commit-confirm.svg)](https://agentmods.dev/skills/legendapp/legend-skills/commit-confirm)
Your own site
<a href="https://agentmods.dev/skills/legendapp/legend-skills/commit-confirm"><img src="https://agentmods.dev/badge/skills/legendapp/legend-skills/commit-confirm.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 395 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 $0.00081 $0.00395
Opus 5 $0.00041 $0.00198
Sonnet 5 $0.00016 $0.00079
Haiku 4.5 $0.00008 $0.00040

Measured 5d ago against content hash ce9299cf7793, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-confirm 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 5d 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.

commit-confirm/SKILL.md · 32 lines

What it actually says

Commit Confirm

Use this wrapper only after the explicit opt-in described in the frontmatter. A normal approval-first commit request does not opt in to this skill or its whole-working-tree default.

Use this skill to run $commit in approval-first mode, defaulting to the whole working tree.

Before starting, load and follow $commit. This skill overrides its default scope and approval behavior; $commit owns working-tree inspection, grouping, message style, staging, committing, and reporting.

Selected installs do not install dependencies automatically. If $commit is not installed or available, stop before staging or committing. Tell the user to install it with:

npx skills add LegendApp/legend-skills --skill commit

Then ask them to retry after installation.

Scope And Approval Override

When using $commit, force plan mode:

  • Unless the user requests a narrower scope, use all-changes mode: inspect staged, unstaged, and untracked changes as the pool to group. Preserve explicit exclusions.
  • If the user names a subset or asks for only the current agent's changes, honor that narrower scope.
  • Always present a commit plan first and wait for explicit approval such as go.
  • Do not stage or commit before approval, even if there is only one logical commit.
  • After approval, create all agreed commits without asking again unless the working tree changes unexpectedly.
  • Treat go after a previously presented plan as approval for that plan, then re-check the working tree before staging.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 32 lines · 81 tokens per session scan A ce9299cf7793

Subscribe to this mod's changes

commit-confirm is a skill published in the GitHub repository LegendApp/legend-skills (37 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 395 once invoked, about $0.0004 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.