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.
npx agentmods add rules/benwilcock/rhdh-lab/git-githubgit clone --depth 1 https://github.com/benwilcock/rhdh-labWhat 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 | $0.00571 | $0.00571 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
git-github 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git & GitHub Conventions
Commit Messages
Write clear, detailed commit messages that explain why the change was made, not just what changed.
Format
<short summary in imperative mood, max ~72 chars>
<optional body: explain motivation, context, trade-offs, or anything
non-obvious about the change. Wrap lines at ~72 chars.>
Guidelines
- Use imperative mood: "Add feature" not "Added feature" or "Adds feature"
- First line is a concise summary; add a blank line then a body for anything non-trivial
- Reference related docs or issues when relevant (e.g. "See docs/architecture.md")
- Group related changes into a single commit; separate unrelated changes into distinct commits
Email & Identity
This repository uses a GitHub noreply email to keep the author's personal email private.
- NEVER change
user.emailin git config - NEVER use a personal email address in commits
- The repo-level config is already set; do not override it
Secret Safety
Before every commit:
- Run
git diff --stagedand review for secrets, credentials, personal paths, or tokens - NEVER commit files matching:
.env,*-credentials.yaml,*.pem,*.key - NEVER commit hardcoded passwords, API keys, tokens, or personal absolute paths (e.g.
/Users/...,/home/...) - Use
${ENV_VAR}references for all secrets; set real values only in the gitignored.env - If in doubt, check
.gitignorecovers the file before staging
Submodule: rhdh-local
rhdh-local/is a git submodule tracking the upstream RHDH Local projectmodified: rhdh-local (untracked content)ingit statusis normal -- do not try to fix it- NEVER stage or commit changes inside
rhdh-local/ - To update the submodule:
cd rhdh-local && git checkout main && git pull origin main && cd ..then commit the new SHA in rhdh-lab
Force Push
- NEVER force push to
mainunless the user explicitly requests it - When rewriting history (e.g. email changes, squashing), always use
--force-with-leasefirst; only fall back to--forceif lease fails due to the rewrite itself
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.
- yesterday First seen · 57 lines · 571 tokens per session scan A 0f624496d9c0
git-github is a cursor rule published in the GitHub repository benwilcock/rhdh-lab (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 571 tokens to every session, about $0.0029 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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.