vibeyard: Command for Claude Code

.claude/commands/commit.md

commit is a command for Claude Code from elirantutia/vibeyard. It costs 0 tokens per session (714 once invoked), scanned A, original, MIT.

A command workflow for creating a Git commit, which records selected project changes in version control.

In plain words
What is it for?
It is for reviewing changes, running the project's tests, staging relevant files, choosing a structured commit prefix, and creating the commit.
Why use it?
It checks the working tree and tests before committing, helping avoid recording unrelated files or known failures.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is elirantutia/vibeyard's own configuration. It tells Claude Code how to work on vibeyard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vibeyard configures →

About the project

Vibeyard is an IDE and project workspace for managing multiple AI coding-agent sessions, including parallel runs, split panes, task boards, cost tracking, and session resumption. It is for developers who use Claude Code, Codex CLI, or Gemini CLI and need to organize many agent-driven coding tasks. The catalogue add-ons provide commands, skills, and instructions for working with Vibeyard.

elirantutia/vibeyard · 1,389 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to elirantutia/vibeyard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/elirantutia/vibeyard/main/.claude/commands/commit.md
Clone the repo
git clone --depth 1 https://github.com/elirantutia/vibeyard

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/elirantutia/vibeyard/commit/github.svg)](https://agentmods.dev/commands/elirantutia/vibeyard/commit)
Your own site
<a href="https://agentmods.dev/commands/elirantutia/vibeyard/commit"><img src="https://agentmods.dev/badge/commands/elirantutia/vibeyard/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 commit

Your own site · 80×15
<a href="https://agentmods.dev/commands/elirantutia/vibeyard/commit"><img src="https://agentmods.dev/badge/commands/elirantutia/vibeyard/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 714 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 $0.00000 $0.00714
Opus 5.5 $0.00000 $0.00286
Sonnet 5.5 $0.00000 $0.00143
Haiku 4.5 $0.00000 $0.00071

Measured 1mo ago against content hash 60709df62b28, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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.

.claude/commands/commit.md · 60 lines

What it actually says

Create a git commit for the current staged (or unstaged) changes using a structured commit message convention.

Instructions

  1. Inspect the working tree:

    • Run git status (never use -uall) to see untracked and modified files.
    • Run git diff --staged to see what is already staged.
  2. Run tests:

    • Run npm test and verify all tests pass.
    • If any test fails, stop and report the failure — do NOT proceed with the commit.
  3. Stage files if nothing is staged:

    • If there are no staged changes but there are modified/untracked files, stage the relevant ones.
    • Only stage files that are relevant to the current task or session. Do NOT stage unrelated changes that happen to exist in the working tree.
    • NEVER stage files that likely contain secrets (.env, credentials.json, .key files, etc.).
    • Prefer staging specific files by name over git add -A.
  4. Analyze the changes and choose a prefix: Pick the most appropriate prefix based on the nature of the changes:

    Prefix When to use Release Notes Section
    add New feature, file, or capability Features
    feat New feature (alternative to add) Features
    implement Completing a planned feature Features
    introduce Introducing a new concept or component Features
    support Adding support for something new Features
    fix Bug fix or correction Fixes
    resolve Resolving an issue Fixes
    patch Small targeted fix Fixes
    correct Correcting wrong behavior Fixes
    improve Enhancement to existing functionality Changes
    update Updating existing behavior or dependencies Changes
    remove Removing code, features, or files Changes
    refactor Code restructuring without behavior change Changes
    bump Version bump Changes
  5. Format the commit message:

    • Format: <prefix> <concise lowercase description>
    • Examples: add dark mode support, fix session resume on restart, refactor PTY lifecycle management
    • Keep it concise — one line, no period at the end
    • Focus on the "what" and "why", not the "how"
  6. If $ARGUMENTS is provided, use it as guidance or context for the commit message. It may be a description of what was done, a hint about the prefix to use, or a full message to refine.

  7. Create the commit using a HEREDOC for the message:

    git commit -m "$(cat <<'EOF'
    <prefix> <description>
    EOF
    )"
    
  8. Verify by running git status after the commit to confirm success.

  9. Do NOT push to the remote unless explicitly asked.

$ARGUMENTS

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 · 60 lines · 0 tokens per session scan A 60709df62b28

Subscribe to this mod's changes

commit is a command published in the GitHub repository elirantutia/vibeyard (1,389 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 714 tokens. 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.