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 BOXELS/cursor-rules --skill setup-rulesgit clone --depth 1 https://github.com/BOXELS/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/boxels/cursor-rules/setup-rules)<a href="https://agentmods.dev/skills/boxels/cursor-rules/setup-rules"><img src="https://agentmods.dev/badge/skills/boxels/cursor-rules/setup-rules/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/boxels/cursor-rules/setup-rules"><img src="https://agentmods.dev/badge/skills/boxels/cursor-rules/setup-rules.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 | $0.00130 | $0.02894 |
| Opus 5.5 | $0.00052 | $0.01158 |
| Sonnet 5.5 | $0.00026 | $0.00579 |
| Haiku 4.5 | $0.00013 | $0.00289 |
Grade A, and why
setup-rules 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 12d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Rules
Fill in the rule templates one file at a time. The user may not be technical: explain in plain language, recommend rather than ask open-ended questions when they're unsure, and never assume knowledge of frameworks or tooling.
Start by switching to Plan mode if available.
Shipped files (only these eight)
Fill exactly these files, in this order. Do not edit any other file in .cursor/rules/.
product.mdctech.mdcsecurity.mdcdesign.mdcstructure.mdcdocumentation.mdcmodels.mdcglobal-rules.mdc
The one exception outside .cursor/rules/ is the model: line in .cursor/agents/worker.md, which you set during step 7 (models.mdc). Touch nothing else in that file.
Never edit template-repo.mdc. That file is maintainer-only for the cursor-rules template repository. Never fill placeholders in files that are not in this list.
Step 0 — template-repo.mdc (before anything else)
If .cursor/rules/template-repo.mdc is absent, continue to detect new vs existing.
If it exists, stop and ask one question. Do not infer the answer:
This folder still has
template-repo.mdc, which belongs only to the cursor-rules template repository. Are you (A) maintaining the template — I'll stop and leave every file alone — or (B) starting a real project from a clone or full-folder copy — I'll deletetemplate-repo.mdcand continue setup?
- A: Stop. Do not write or delete anything.
- B: Delete
.cursor/rules/template-repo.mdc, then continue. Do not editREADME.mdor other project files as part of setup.
Step 1 — Detect: new project or existing code?
Before asking anything, look at the project root (ignore .cursor/, .git/, AGENTS.md, README.md, LICENSE).
Signals of an existing project (any one is enough):
- A dependency manifest:
package.json,pyproject.toml,requirements.txt,Gemfile,go.mod,Cargo.toml,pubspec.yaml,composer.json,*.csproj,Package.swift,build.gradle*. - Source directories with code in them:
src/,app/,lib/,pages/,server/,api/, or similar. - A migrations or schema folder:
supabase/,prisma/,migrations/,alembic/,db/. - Hosting or CI config:
netlify.toml,vercel.json,Dockerfile,fly.toml,railway.json,.github/workflows/.
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.
- 12d ago Changed · +3 lines 71741ca4cf8d
- 1mo ago Changed · +26 lines · +25 tokens per session f1af4714c7f3
- 1mo ago First seen · 121 lines · 105 tokens per session scan A 70afae8b49d2
setup-rules is a skill published in the GitHub repository BOXELS/cursor-rules (6 stars, last pushed 12d ago), licensed MIT. It adds 130 tokens to every session and 2,894 once invoked, about $0.0005 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 2026-09-15.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.