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/elumenotion/guideants/git-branch-and-push-safetygit clone --depth 1 https://github.com/Elumenotion/GuideAntsWrote 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/elumenotion/guideants/git-branch-and-push-safety)<a href="https://agentmods.dev/rules/elumenotion/guideants/git-branch-and-push-safety"><img src="https://agentmods.dev/badge/rules/elumenotion/guideants/git-branch-and-push-safety.svg" alt="Measured on agentmods" 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 | $0.00436 | $0.00436 |
| Opus 5 | $0.00218 | $0.00218 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
git-branch-and-push-safety 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 6d 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.
What it actually says
Git Branch and Push Safety
Agent restrictions
- Never run
git pushin any form unless the user explicitly asks in the current message. - Never run
git push --forceorgit push --force-with-leasetomainormaster. - Never run
git commit(see commit-ownership rule). - When the user asks to push, verify upstream first and show them the exact command; prefer
git push -u origin HEADon a feature branch.
Creating a feature branch (required pattern)
Always create feature branches from updated main and set upstream to the same branch name on origin:
git fetch origin
git checkout main
git pull origin main
git checkout -b feature/<name>
git push -u origin feature/<name>
Never use any of these on a feature branch:
git push -u origin maingit push origin HEAD:maingit branch --set-upstream-to=origin/main(while not onmain)
Verify before any push (user or agent handoff)
git branch -vv
git rev-parse --abbrev-ref --symbolic-full-name @{u}
Upstream must be origin/<same-branch-name>, not origin/main, unless the current branch is literally main.
If upstream is wrong on a feature branch:
git branch --set-upstream-to=origin/feature/<name> feature/<name>
Local hook (install once per clone)
.\scripts\install-git-hooks.ps1
This installs .githooks/pre-push, which blocks pushing a non-main branch to origin/main.
GitHub (already configured)
main requires pull requests. Force-push rules may be bypassable by admins — the local hook is the last line of defense before push.
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.
- 6d ago First seen · 59 lines · 436 tokens per session scan A 270d820edbeb
git-branch-and-push-safety is a cursor rule published in the GitHub repository Elumenotion/GuideAnts (57 stars, last pushed 2d ago), licensed Apache-2.0. It adds 436 tokens to every session, about $0.0022 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.
Other cursor rules, from other repositories
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.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.