commit-changes-main

A Git workflow for committing changes directly to the main branch, the shared branch commonly used for the project's ready-to-merge code.

In plain words
What is it for?
Use it when you explicitly approve committing and pushing a completed change directly to main or master.
Why use it?
It applies extra permission checks to avoid unintended changes on a shared branch while keeping the commit message consistent and excluding secrets.

Skill for Claude CodeCodexCursor

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/emaraschio/cursor-commands/commit-changes-main
Any agent
npx skills add emaraschio/cursor-commands --skill commit-changes-main
Clone the repo
git clone --depth 1 https://github.com/emaraschio/cursor-commands

Made for: Claude Code, Codex, Cursor.

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 276 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 $0.00013 $0.00276
Opus 5 $0.00006 $0.00138
Sonnet 5 $0.00003 $0.00055
Haiku 4.5 $0.00001 $0.00028

Measured 2d ago against content hash 852326b78aee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-changes-main 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.

.cursor/skill-contracts/commit-changes-main/SKILL.md · 42 lines

What it actually says

Overview

Commit changes to the main branch of a GitHub repository with proper commit message.

Steps

  1. Prepare branch

    • Ensure all changes are committed to the correct branch using the conventional commit message convention
    • Push changes to remote
    • Verify changes are up to date with main
  2. Write commit message

    • Must use the conventional commit message convention.
    • Summarize changes clearly
  3. Commit changes

    • Use a single commit for the changes
    • Commit the changes to the main branch
    • Push the main branch to the remote repository

Commit Message Examples

feat: add new feature
fix: fix bug
chore: update dependencies
refactor: refactor code
test: add tests
docs: update documentation

Guardrails

  • Commit to main only with explicit consent; otherwise move the work to a separate branch.
  • Never force-push main or any shared branch; reconcile with a normal pull or merge instead.
  • Use the Conventional Commits convention for every message.
  • Never print, stage, or commit secrets or credential files (.env, .env.*, keys); exclude them and warn instead.
Files

What ships with it

3 files 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. 2d ago First seen · 42 lines · 13 tokens per session scan A 852326b78aee

Subscribe to this mod's changes

commit-changes-main is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 25d ago), licensed MIT. It adds 13 tokens to every session and 276 once invoked, about $0.0001 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

commit

Prepare and propose a commit. Use when the user asks to commit, prepare a commit, or similar. Never commits without explicit approval.

hlalljie/agent-workflow-presets · 29 tokens

phase-summary

Produce the deliverables summary at the end of a task loop. Always run before preparing a commit.

hlalljie/agent-workflow-presets · 23 tokens

managing-git

Manages Git workflows including branching, commits, and pull requests. Use when working with Git, creating commits, opening PRs, managing branches, resolving conflicts, or when asked about version control best practices.

CloudAI-X/claude-workflow-v2 · 46 tokens

git-commit

This skill should be used BEFORE running any git commit command. Triggers when about to run git commit. Ensures commit messages follow Conventional Commits specification and prompts for the Jira ticket number.

fredrikaverpil/dotfiles · 43 tokens

git-commit

How to write a commit message that stays meaningful after the session ends — explain WHY, follow the repository's convention, and never reference conversation-local structure like "Phase 2" or "Task 3". Load this BEFORE running git commit, whenever creating a commit, amending a commit message, or asked to "commit…

natsukium/dotfiles · 88 tokens

ship-it

End-to-end ship loop: atomic commits, PR, tiered review (lite|heavy), fix every finding, re-review until zero remain, then merge-commit. lite runs a single /review pass; heavy spins up a dynamic Workflow with diff-aware review personas plus a Codex cross-model peer. Use when Stevie says "/ship-it", "ship it", "ship…

stevengonsalvez/agents-in-a-box · 96 tokens