git-github-workflow

A set of Git and GitHub working rules for creating commits and submitting pull requests. Git records code changes, while GitHub hosts repositories and reviews.

In plain words
What is it for?
Use it when asked to commit changes or open a pull request, including checking the changed files, creating an English Conventional Commit, pushing the branch, and preparing the request.
Why use it?
It makes the required checks, commit format, branch review, and pull-request steps consistent.

Cursor rule 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 rules/sotayamashita/openapi-mcp-server/git-github-workflow
Clone the repo
git clone --depth 1 https://github.com/sotayamashita/openapi-mcp-server

Made for: Cursor.

Per session 253 This file is loaded in full into every session.
When invoked 253 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 $0.00253 $0.00253
Opus 5 $0.00127 $0.00127
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00025 $0.00025

Measured yesterday against content hash a6e8c016a006, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-github-workflow 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/rules/git-github-workflow.mdc · 21 lines

What it actually says

When asked, to create a commit:

  1. Run git status to check changes
  2. Run git commit following Conventional Commits format in English (<type>[optional scope]: <description>)
  3. Help commit meaningful units of change rather than staging everything
  4. Use git diff [optional file(s)] | cat when diff is needed.

When asked, to submit a PR (Note: Use gh and assume I am already authenticated correctly):

  1. Run git status to check changes
  2. Run git add . to add all the changes to the staging area (IF NEEDED)
  3. Run git commit to commit changes (IF NEEDED)
  4. Run git push to push the changes to the remote repository (IF NEEDED)
  5. Run git branch to check the current branch
  6. Run git log main..[Insert current branch]
  7. Run git diff --name-status main to check to see what files have been changed
  8. Run gh pr create --title "Title goes here..." --body "Example body..."
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 · 21 lines · 253 tokens per session scan A a6e8c016a006

Subscribe to this mod's changes

git-github-workflow is a cursor rule published in the GitHub repository sotayamashita/openapi-mcp-server (7 stars, last pushed 2d ago), licensed MIT. It adds 253 tokens to every session, about $0.0013 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.