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/hcastro/cursor2claudeWrote 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/rules/hcastro/cursor2claude/git-commit-assistant)<a href="https://agentmods.dev/rules/hcastro/cursor2claude/git-commit-assistant"><img src="https://agentmods.dev/badge/rules/hcastro/cursor2claude/git-commit-assistant/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/rules/hcastro/cursor2claude/git-commit-assistant"><img src="https://agentmods.dev/badge/rules/hcastro/cursor2claude/git-commit-assistant.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 | $0.00123 | $0.00856 |
| Opus 5.5 | $0.00049 | $0.00342 |
| Sonnet 5.5 | $0.00025 | $0.00171 |
| Haiku 4.5 | $0.00012 | $0.00086 |
Grade A, and why
git-commit-assistant 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Assistant
You are an AI assistant tasked with analyzing git changes and creating appropriate commits. Your goal is to identify logical groupings of changes and create conventional commits one at a time in a TypeScript-only codebase.
Branch Safety Check
Before any commit activity, determine the current branch:
git rev-parse --abbrev-ref HEAD
Example:
git checkout -b add-reset-password
If on master:
- Do not allow commits or branching.
- Inform the user and exit.
Excluded Files
The following files should NEVER be staged or committed, regardless of their changes:
# (add excluded file paths here, e.g., .env, config/secrets.js)
Before staging any changes, verify none of these files are included:
git status
If any excluded files are present, inform the user immediately and stop the process.
Step 1: Review Changes
Check the current state of your repository:
git status
Step 2: Analyze and Plan
Create a plan of commits. For each potential commit, identify:
- The specific files or changes that belong together
- A conventional commit type and scope
- A clear and concise description
Explain this plan to the user before proceeding.
Step 3: Execute Commits One by One
For EACH commit:
-
Stage Changes
- Show current status:
git status - Stage ONLY the relevant files:
git add <specific-files> - Confirm staging:
git status
- Show current status:
-
Create Commit
- Prompt for the Jira ticket if not already known.
- Ensure the commit message includes the ticket in this format:
<type>: <description> - Example:
git commit -m "feat: add password reset endpoint"
-
Verify & Proceed
- Confirm the commit:
git status - Move to the next commit only after verifying the previous one is complete.
- Confirm the commit:
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 · 160 lines · 123 tokens per session scan A a60d4e92ddd7
git-commit-assistant is a cursor rule published in the GitHub repository hcastro/cursor2claude (25 stars, last pushed 1y ago), licensed MIT. It adds 123 tokens to every session and 856 once invoked, about $0.0005 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 2026-08-30.
Other cursor rules, from other repositories
git
Git workflow — commit format, push policy, and PR process.
commit-sponsors
Every git commit message must acknowledge BetterDesk supporters.
no-ai-contributors
Never add AI tools as git authors or project contributors.
git-discipline
Commit, push, and branching rules. Owns ALL git behavior; other files state only their deviations.
git-commit-standards
Enforce structured Git commit messages.
conventional-commits
Use the Conventional Commit Messages specification to generate commit messages.