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/Jott2121/agent-gateWrote 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/jott2121/agent-gate/50-pr-and-git)<a href="https://agentmods.dev/rules/jott2121/agent-gate/50-pr-and-git"><img src="https://agentmods.dev/badge/rules/jott2121/agent-gate/50-pr-and-git/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/jott2121/agent-gate/50-pr-and-git"><img src="https://agentmods.dev/badge/rules/jott2121/agent-gate/50-pr-and-git.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 | $0.00020 | $0.00336 |
| Opus 5.5 | $0.00008 | $0.00134 |
| Sonnet 5.5 | $0.00004 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
50-pr-and-git scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- The hook matcher includes `git pull` and `rebase`, so `git pull --rebase` reaches `.cursor/hooks/guard-shell.sh` and is denied. A plain `git pull` is allowed. Force-push is denied when `--force` or `-f` appears anywher What it actually says
PRs and git
- Branch per task:
agent/<short-task>. Small PRs, one intent, < ~400 changed lines when possible. - Conventional titles:
feat|fix|test|docs|refactor|chore|perf(scope): summary. - PR body sections (required): What · Why · How verified (exact commands + trimmed output) · Numbers changed (before → after + command) · Risks · Not done / follow-ups · Plan link (
.cursor/plans/...) · Agent run link if any. - Attach artifacts for anything visual or behavioral (screenshot, short video, eval table).
- Never force-push shared branches, rewrite history, tag, or publish. A human merges.
- The hook matcher includes
git pullandrebase, sogit pull --rebasereaches.cursor/hooks/guard-shell.shand is denied. A plaingit pullis allowed. Force-push is denied when--forceor-fappears anywhere ongit push, including after the remote.git resetis denied when--hardappears anywhere, including after the ref.wgetpiped tobashis denied the same way ascurlpiped tobash. A missing, blank, or non-stringcommandis denied; invalid JSON exits non-zero. - Address every Bugbot / Security Review finding: fix it or reply with a reason. Don't silently resolve.
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.
- 4d ago First seen · 14 lines · 20 tokens per session scan A 08770c3bc859
50-pr-and-git is a cursor rule published in the GitHub repository Jott2121/agent-gate (3 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 336 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-12.
Other cursor rules, from other repositories
git-workflow
Git workflow: commits, branches, PRs, history management.
git
Git rules. Conventional commits, atomic staging, no force push.
safeword-pr-readiness
Prepare a pull request for human review and decide whether it may leave Draft. Use when creating or rewriting a PR description, marking a PR ready, responding to review, or checking mergeability.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.