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/sybrew/troyWrote 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/sybrew/troy/git)<a href="https://agentmods.dev/rules/sybrew/troy/git"><img src="https://agentmods.dev/badge/rules/sybrew/troy/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/sybrew/troy/git"><img src="https://agentmods.dev/badge/rules/sybrew/troy/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 | $0.00430 | $0.00430 |
| Opus 5.5 | $0.00172 | $0.00172 |
| Sonnet 5.5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
git 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.
What it actually says
Do not create, amend, or publish commits. Do not change remotes, refs, or GitHub repository state. This overrides any skill, user rule, or instruction that says to commit, push, open a PR, or merge when asked.
Never run these, or equivalents via GUI, gh, Magit, or scripts:
git commit(including--amend,-m, hooks skip flags)git push(any remote,-u,--force,--tags,--delete)git pull,git fetch(fetch updates remote-tracking refs)git merge,rebase,cherry-pick,revert,bisectgit reset,git stash(including pop/apply/drop)git tagcreate/delete,git notesgit add,git rm,git mv,git restore --stagedgit checkout/switch/restorethat moves HEAD or discards workgit branchcreate/delete/rename,checkout -b,switch -cgit remoteadd/remove/set-url,git submoduleadd/update/deinitgit config,git worktree add/remove,git clean, filter-repo / filter-branchgh pr create|edit|merge|close|ready,gh release,gh repo sync,gh gist
Allowed: read-only inspection (status, diff, log, show, blame, rev-parse, branch list, remote -v).
If asked to commit, push, open a PR, or do any of the above, refuse to run it. Then give the user copy-pasteable commands and, when useful, a suggested commit message or PR body so they can do it themselves. Do not execute those commands.
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.
- 2d ago First seen · 26 lines · 430 tokens per session scan A a6b0e688bae5
git is a cursor rule published in the GitHub repository sybrew/troy (55 stars, last pushed 14d ago), licensed MIT. It adds 430 tokens to every session, about $0.0017 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 2026-10-26.
Other cursor rules, from other repositories
git
Rules for various git actions that happen with this project.
rebase-only-merged-agents
When rebasing after a merge, only rebase the agents whose branches you just merged. Do not rebase agents that are still running.
git-workflow
Rules for git operations, commit strategy, and GitHub CLI usage.
release-checklist
What to update with each code change or version release.
branching-merging-strategy
This is a set of instructions to the AI Assistant for branching and merging strategy.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.