git_workflow_rules

Rules for handling Git save and sharing requests through project scripts. Git is the system that records code changes, while pushing sends commits to a shared remote repository.

In plain words
What is it for?
Use them when the user asks to commit, push, commit and push, or discard changes, including choosing the matching project script.
Why use it?
They distinguish saving changes locally from sending them to others and require clarification when a request is unclear.

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/shawnfromportland/agentmemoryforcursor/git_workflow_rules
Clone the repo
git clone --depth 1 https://github.com/shawnfromportland/agentmemoryforcursor

Made for: Cursor.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,472 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 $0.00019 $0.01472
Opus 5 $0.00010 $0.00736
Sonnet 5 $0.00004 $0.00294
Haiku 4.5 $0.00002 $0.00147

Measured 2d ago against content hash d50d3f3c8296, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git_workflow_rules 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/rules/git_workflow_rules.mdc · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rule Name: Git Workflow Automation

Description:

This rule outlines how the AI assistant should handle requests to commit or discard changes using the custom npm scripts. The goal is to streamline the development workflow by automating these common Git operations based on natural language commands from the user.

Committing Changes

  1. Trigger:

    • For commit ONLY (local): User asks to "commit," "commit changes," "commit this," "commit the latest," or similar explicit phrasing indicating a desire to save work locally.
    • For commit AND PUSH: User asks to "commit and push," "save and sync," or similar explicit phrasing indicating a desire to save work and update the remote repository.
    • For PUSH ONLY: User asks to "push," "push changes," "sync remote," or similar explicit phrasing indicating a desire to update the remote repository with already committed changes.
  2. Clarify Ambiguity (If Necessary):

    • If the user's request to commit (from Trigger) is vague or could be interpreted in multiple ways (e.g., "should we save this?"), the AI MUST first seek clarification: "It sounds like you might want to commit the changes. Is that correct?"
    • If clarification was sought and the user confirms they do not want to commit, the process stops here. The subsequent steps are only followed if the intent to commit is clear (either initially explicit or clarified as such).
  3. Generate Commit Message and Detailed Changelog Content:

    • The AI will silently review changes made during the current interactive session leading up to the commit request.
    • The AI will generate a concise, conventional commit message (e.g., "feat: Implement user authentication flow").
    • The AI will also generate a list of key changes/features/fixes from the session as bullet points.
    • The AI will format this as a markdown block: the commit message as ### Title, followed by the bullet points. Example:
      ### feat: New user dashboard and API refactor
      - Created `UserDashboard.tsx` with initial metrics display.
      - Modified `/api/users` endpoint to support pagination.
      - Refactored `AuthService` to use JWT tokens.
      

Read the full file on GitHub · 77 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 · 77 lines · 19 tokens per session scan A d50d3f3c8296

Subscribe to this mod's changes

git_workflow_rules is a cursor rule published in the GitHub repository shawnfromportland/agentmemoryforcursor (11 stars, last pushed 1y ago), licensed MIT. It adds 19 tokens to every session and 1,472 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 2026-08-30.