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 skills add pekral/cursor-rules --skill benchmarkgit clone --depth 1 https://github.com/pekral/cursor-rulesWrote 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/skills/pekral/cursor-rules/benchmark)<a href="https://agentmods.dev/skills/pekral/cursor-rules/benchmark"><img src="https://agentmods.dev/badge/skills/pekral/cursor-rules/benchmark/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/skills/pekral/cursor-rules/benchmark"><img src="https://agentmods.dev/badge/skills/pekral/cursor-rules/benchmark.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 | $0.00053 | $0.01711 |
| Opus 5.5 | $0.00021 | $0.00684 |
| Sonnet 5.5 | $0.00011 | $0.00342 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
benchmark 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benchmark (Laravel)
Measure real performance baselines for a Laravel app and detect regressions by
comparing before/after a change. This skill measures — it produces honest
numbers and verdicts. For design guidance on hot paths, defer to
@skills/latency-critical-systems/SKILL.md; to act on a regression with an
optimization loop, hand off to @skills/benchmark-optimization-loop/SKILL.md.
Constraints
- Apply
@rules/sql/optimalize.mdcwhen reading or interpreting query timing (N+1, index usage, SARGable filters). - Apply
@rules/code-testing/general.mdcif you add or touch any benchmark test (Pest, nodescribe()). - Measure, never guess — every number must be a real readback from a running system, command, or tool.
- Control for noise: separate warm vs cold, run repeats (≥5), report median plus p95, fix one variable at a time.
- Same machine, same dataset, same config for before and after — note the environment so a teammate can reproduce.
- Keep secrets and private payloads out of baseline JSON and logs.
Use when
- You need a performance baseline for a page, API route, build step, or query.
- A change (PR, dependency bump, query rewrite, config change) may have caused a regression and you must prove it either way.
- You are comparing two implementations or stack options on the same workload.
- Someone claims "it's faster/slower" without a measured before/after.
Do not use for live design advice (use latency-critical-systems) or for
diagnosing one Telescope request (use @skills/laravel-telescope/SKILL.md).
Execution
Pick the modes that match the change. Always record environment first:
app URL, commit SHA, APP_ENV, dataset size, cache/opcache state, and whether
the run is cold (first hit, caches cleared) or warm (steady state).
Mode A — Page performance (Core Web Vitals)
Measure against the running Laravel app (php artisan serve or the real host).
- Run Lighthouse:
npx lighthouse <url> --output=json --output-path=./lh.json --only-categories=performance --chrome-flags="--headless". - Capture: LCP (target < 2.5s), CLS (< 0.1), INP (< 200ms), FCP (< 1.8s), TTFB (< 0.8s).
- Capture resource weight: total transfer, JS/CSS bytes (post-Vite build), render-blocking resources, request count.
- Run 3–5 times; report median. Lighthouse is noisy — discard the first (cold) run unless cold is the metric you want.
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 · 119 lines · 53 tokens per session scan A b5c50cf640d1
benchmark is a skill published in the GitHub repository pekral/cursor-rules (11 stars, last pushed 19d ago), licensed MIT. It adds 53 tokens to every session and 1,711 once invoked, about $0.0002 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 skills, from other repositories
knossos
Use when you need to know what depends on something, what a change would break, where a new file belongs, how a request reaches a given component, or who calls a function, in a repository that Knossos has scanned. Answers come from a static graph with file and line evidence instead of from reading the source tree.…
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
create-powergrid-plugin
Create a complete PowerGrid plugin from scratch, including PHP class, Column macro, Blade view, Alpine.js component, and registration.
sentry-php-sdk
Full Sentry SDK setup for PHP. Use when asked to "add Sentry to PHP", "install sentry/sentry", "setup Sentry in PHP", or configure error monitoring, tracing, profiling, logging, metrics, crons, or AI monitoring for PHP applications. Supports plain PHP, Laravel, and Symfony.
owl-admin-devtools-generator
A development guide for Owl Admin, a Laravel-based administration system, covering its code generator, API templates, relationships, and visual pages.
owl-admin-extension-module
A development guide for Owl Admin extensions and modules. An extension adds optional functionality, while a module groups related routes, settings, menus, and permissions.