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/louisbrulenaudet/monorepo-templateWrote 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/louisbrulenaudet/monorepo-template/worktrees)<a href="https://agentmods.dev/rules/louisbrulenaudet/monorepo-template/worktrees"><img src="https://agentmods.dev/badge/rules/louisbrulenaudet/monorepo-template/worktrees/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/louisbrulenaudet/monorepo-template/worktrees"><img src="https://agentmods.dev/badge/rules/louisbrulenaudet/monorepo-template/worktrees.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 | $0.00000 | $0.00332 |
| Opus 5.5 | $0.00000 | $0.00133 |
| Sonnet 5.5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
worktrees 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 23d 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
Worktrees
worktree.symlinkDirectoriescannot replace the per-worktreepnpm install(rootAGENTS.md): pnpm keeps anode_modulesat the root and in every workspace package, and a symlinked root one would make a worktree install write into the main checkout. The install hardlinks from the store, so it costs CPU once, not disk.worktree.sparsePathsis applied as a cone-mode sparse checkout: every root-level file is checked out whether listed or not; only directories are filtered. The directory entries do the work (.agents,.changeset,.claude,.cspell,.cursor,.github,.playwright,.vite-hooks,.vscode,apps,hooks,packages); the root-file entries stay so the list is still correct if the checkout stops being cone-mode. Add any new root directory the tooling needs;.opencodeis excluded on purpose..worktreeincludecopies matching gitignored files into each new worktree. It has no patterns today, so a worktree starts with cold Turbo and Node compile caches. Never add env or credential files - provision isolated credentials per worktree (guardrails.mdc). AWorktreeCreatehook would disable.worktreeincludeentirely, which is why there is none.
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.
- 23d ago Changed · -1 lines bd1a01537798
- 25d ago First seen · 13 lines · 0 tokens per session scan A 03af1c24f06b
worktrees is a cursor rule published in the GitHub repository louisbrulenaudet/monorepo-template (19 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 332 tokens. 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 2026-09-28.
Other cursor rules, from other repositories
mcp-releasing
Steps and procedures for releasing MCP (Model Context Protocol) servers as NPM packages.
commit
Create well-formatted commits with conventional commit messages and emojis.
add-to-changelog
Update the project's CHANGELOG.md file with a new entry.
analyze-issue
Fetch GitHub issue details and create a comprehensive implementation specification.
commit-fast
Generate 3 commit message suggestions based on the staged changes, then automatically use the first suggestion without user confirmation.
bug-fix
Streamline bug fixing workflow from issue creation to pull request.