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.
git clone --depth 1 https://github.com/emaraschio/cursor-commandsWrote 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.
[](https://agentmods.dev/commands/emaraschio/cursor-commands/commit-changes-main)<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/commit-changes-main"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/commit-changes-main/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.
<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/commit-changes-main"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/commit-changes-main.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00013 | $0.00386 |
| Opus 5.5 | $0.00005 | $0.00154 |
| Sonnet 5.5 | $0.00003 | $0.00077 |
| Haiku 4.5 | $0.00001 | $0.00039 |
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 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.
What it actually says
Overview
Commit directly on main/master when explicitly allowed. Full workflow: .cursor/skill-contracts/commit-changes-main/SKILL.md (user install: ~/.cursor/skill-contracts/commit-changes-main/SKILL.md).
Defaults
None. See skill for workflow defaults.
Steps
- Read
.cursor/skill-contracts/commit-changes-main/SKILL.mdfor the full agent contract; if that file is missing, read~/.cursor/skill-contracts/commit-changes-main/SKILL.md. - Execute the workflow in order; do not skip safety steps.
- Report outcomes per skill (summary, tables, or checklist as specified).
Anti-patterns
- Commit to main only with explicit consent. Trigger: changes are ready while the current branch is main or master. Wrong: committing or pushing to the shared default branch without being asked. Correct: confirm explicit consent first, otherwise move the work to a separate branch. Reason: commits to a shared default branch land for everyone immediately and are disruptive to undo.
- Never force-push main. Reason: a force-push to a shared branch rewrites published history teammates have already pulled, which can erase their work.
Examples
/commit-changes-main
Maintainers
Behavioral eval: .cursor/skill-contracts/commit-changes-main/eval/cases.md. Ship gate sections: A, S before changing SKILL.md or this command.
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.
- 1mo ago First seen · 38 lines · 13 tokens per session scan A 4edd52cdcfee
commit-changes-main is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 14d ago), licensed MIT. It adds 13 tokens to every session and 386 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
deadcode
Find dead code with a configured Knip baseline, then delete it by category behind a ratchet.
update-deps
Audit outdated dependencies, research breaking changes, update one at a time, verify each, commit separately.
commit
Create one conventional commit from an already-scoped change; never push.
release-prep
Review the local working tree, commit, push, open a PR, drive it merge-ready — do not merge.
commit-msg
Cursor tooling: skills, rules, subagents.
commit
Git commit with conventional commits format.