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/ousid/leanWrote 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/ousid/lean/lean)<a href="https://agentmods.dev/rules/ousid/lean/lean"><img src="https://agentmods.dev/badge/rules/ousid/lean/lean/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/ousid/lean/lean"><img src="https://agentmods.dev/badge/rules/ousid/lean/lean.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 | $0.00221 | $0.00221 |
| Opus 5.5 | $0.00088 | $0.00088 |
| Sonnet 5.5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
lean 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 1mo 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
Answer densely. Cut filler, keep all technical signal.
- Start with the answer. No "Sure", "I'd be happy to", "Let me", no restating the question.
- Fragments over sentences, one idea per line, no closing summary.
- NEVER change code, commands, paths, error strings, config values, or identifiers. Keep them byte for byte exact. Compress prose only.
- GATE: compress only when the reply is mostly prose AND longer than ~40 words. Short replies, pure code blocks or diffs, and tool heavy edits get answered normally with no scaffolding.
- Laravel/PHP: keep framework terms verbatim (Eloquent, Artisan, Blade,
php artisan, facades). Assume framework fluency, do not re-explain basics. For a bug, name theClass::method, then the cause, then the fix.
Do not print token savings figures. Measurement is external (lean-stats).
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.
- 1mo ago First seen · 15 lines · 221 tokens per session scan A c996a9dd1c18
lean is a cursor rule published in the GitHub repository ousid/lean (4 stars, last pushed 2mo ago), licensed MIT. It adds 221 tokens to every session, about $0.0009 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 2026-08-31.
Other cursor rules, from other repositories
vibeflow
Vibeflow spec-driven development methodology — guardrails, pipeline, and project knowledge system.
vibeflow-architect
Vibeflow Architect persona — senior software architect and technical PM for planning, speccing, and auditing. Activates when discussing architecture, specs, PRDs, prompt packs, or audits.
16-wechat-sdk
A set of rules for connecting a Laravel application to WeChat, a widely used Chinese messaging and services platform, through the EasyWeChat software library. It requires application code to use the project's WechatManager wrappers instead of calling the library directly.
15-config-center
Laravel rules for reading dynamic settings through a shared ConfigCenter service or helper instead of querying the settings database table directly. Settings are addressed with dot-separated paths and converted to the expected data types.
00-project
A project rule describing a lightweight administration system built with Laravel, Blade, Vue 3, and Element Plus.
99-guard
A Cursor rule file that marks certain folders as protected and limits some changes and dangerous operations.