Copilot-Skills lazycommit.instructions.md

A set of instructions for creating Git commits with messages based on the changes in the project. It follows the Conventional Commits style, which labels changes such as features, fixes, documentation, tests, or maintenance.

In plain words
What is it for?
Use it to inspect staged or unstaged changes, draft a conventional commit message, and prepare a commit for user approval.
Why use it?
It helps produce a clear commit message from the actual file diff instead of relying on guesswork. The workflow also requires approval before staging and committing changes.

Instructions file for GitHub Copilot

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 instructions/thesethrose/copilot-skills/lazycommit
Clone the repo
git clone --depth 1 https://github.com/TheSethRose/Copilot-Skills

Made for: GitHub Copilot.

Per session 1,177 This file is loaded in full into every session.
When invoked 1,177 The same file — it is already loaded in full.
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 $0.01177 $0.01177
Opus 5 $0.00589 $0.00589
Sonnet 5 $0.00235 $0.00235
Haiku 4.5 $0.00118 $0.00118

Measured 2d ago against content hash a20bc1a3a1ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Copilot-Skills lazycommit.instructions.md 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.

.github/instructions/lazycommit.instructions.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lazycommit Skill - Automatic Context Instructions

Related Prompt: /lazycommit
Related Skill: .github/copilot-skills/lazycommit/

Triggers: commit, auto commit, generate commit, write commit message, make a commit, stage and commit, lazy commit

Context: AI-Powered Commit Message Generation

When working with commits or when user queries contain commit-related keywords, this context is automatically activated.

Core Principles

Mimic Lazycommit Behavior

  • Stage: Detect staged changes (or stage all if nothing staged)
  • Analyze: Build diff context with file summary and numstat
  • Generate: Use Claude to create conventional commit message
  • Confirm: Show message and let user approve/edit/regenerate
  • Execute: Commit only after user approval

Conventional Commits Format

<type>(<scope>): <subject>

Types: feat, fix, docs, style, refactor, perf, test, chore

Subject: imperative mood, lowercase, no period, <90 chars

Quality Standards

  • Single-line messages (unless user requests body)
  • Descriptive scope (e.g., auth, api, ui, deps)
  • Clear intent (what changed and why it matters)
  • Follows conventions consistently

Default Behaviors

When user says "commit" or "auto commit"

  1. Check git status --short for staged changes
  2. If nothing staged: run git add .
  3. Get list of changed files: git diff --cached --name-only
  4. Generate prompt with: file list, numstat, and full diff (truncated if >10KB)
  5. Ask Claude to generate conventional commit message
  6. Automatically commit: git commit -m "message"
  7. Display the committed message to user

When user says "generate commit message"

  1. Same as "commit" workflow
  2. Generates and automatically commits the message

When user says "make a commit"

  1. Same as "commit"
  2. Full workflow end-to-end

When user requests "stage and commit"

  1. Explicitly stage all changes
  2. Generate and commit in one flow

Quality Guidelines

Read the full file on GitHub · 179 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 · 179 lines · 1,177 tokens per session scan A a20bc1a3a1ea

Subscribe to this mod's changes

Copilot-Skills lazycommit.instructions.md is an instructions file published in the GitHub repository TheSethRose/Copilot-Skills (3 stars, last pushed 8mo ago), licensed MIT. It adds 1,177 tokens to every session, about $0.0059 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.