commit

A command guide for committing the current work to Git, the version-control system used to record code changes.

In plain words
What is it for?
Use it when the user explicitly asks to create a Git commit; it also documents that later commits require separate permission.
Why use it?
It provides a consistent commit format and reminds the agent to review which files belong to the current change.

Command for Cursor

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 commands/eamonboyle/mssql-mcp/commit
Clone the repo
git clone --depth 1 https://github.com/eamonboyle/mssql-mcp

Made for: Cursor.

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 168 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 $0.00000 $0.00168
Opus 5 $0.00000 $0.00084
Sonnet 5 $0.00000 $0.00034
Haiku 4.5 $0.00000 $0.00017

Measured yesterday against content hash 7a9b7ab2c603, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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/commands/commit.md · 22 lines

What it actually says

Commit current work

Commit current work.

Important

  • Prepend GIT_EDITOR=true to all git commands you run, especially the ones looking at diffs, so you can avoid getting blocked as you execute commands
  • If you can't get any information from git diff, just using your working memory to determine what has changed

Instructions

Review each file individually to make sure they're related to the work you just did, then write a brief commit message in the following format:

  • Short title description (< 80 characters)
  • 2~3 bullet points (< 80 characters) with a quick description

Notes

  • You should only commit work when instructed. Do not keep committing subsquent work unless explicitly told so

Optional: ask me if I would like to push the commit. (Only if I'm not on main)

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. yesterday First seen · 22 lines · 0 tokens per session scan A 7a9b7ab2c603

Subscribe to this mod's changes

commit is a command published in the GitHub repository eamonboyle/mssql-mcp (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 168 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 2026-08-31.