Borrowing it
Nothing to install: this file belongs to mckinsey/agents-at-scale-ark. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mckinsey/agents-at-scale-ark/main/.cursorrulesgit clone --depth 1 https://github.com/mckinsey/agents-at-scale-arkWrote 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/mckinsey/agents-at-scale-ark/cursorrules)<a href="https://agentmods.dev/rules/mckinsey/agents-at-scale-ark/cursorrules"><img src="https://agentmods.dev/badge/rules/mckinsey/agents-at-scale-ark/cursorrules/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/mckinsey/agents-at-scale-ark/cursorrules"><img src="https://agentmods.dev/badge/rules/mckinsey/agents-at-scale-ark/cursorrules.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 | $0.00351 | $0.00351 |
| Opus 5.5 | $0.00140 | $0.00140 |
| Sonnet 5.5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
cursorrules 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 2mo 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
Cursor Rules for ARK Project
Commit Message Format
MANDATORY: All commit messages and PR titles must follow conventional commit format:
- feat: new feature
- fix: bug fix
- docs: documentation changes
- chore: maintenance tasks
- refactor: code refactoring
- test: adding tests
- ci: CI/CD changes
- build: build system changes
- perf: performance improvements
Examples:
- feat: add agent deployment workflow
- fix: resolve memory leak in executor
- docs: update installation guide
Non-conventional commits will be rejected by automated checks.
Code Style
- Follow existing patterns in the codebase
- No comments unless explicitly requested
- Use absolute paths for file operations
- Prefer editing existing files over creating new ones
Pull Request Format
When creating pull requests, use this simple format:
## Summary
- Brief description of changes
DO NOT include "Test plan" sections in PR descriptions.
Personal/Experimental Files
MANDATORY: All personal documentation, experimental tests, and working artifacts must be placed in the vibe_artifacts/ directory at the repository root.
- ✅ Correct:
vibe_artifacts/QUERY_DEEP_DIVE.md - ✅ Correct:
vibe_artifacts/a2a-streaming-error-test/ - ❌ Incorrect:
QUERY_DEEP_DIVE.md(root level) - ❌ Incorrect:
tests/a2a-streaming-error-test/(unless it's an official test)
The vibe_artifacts/ folder is gitignored and is intended for personal working documents, experimental code, and temporary artifacts that don't need to be committed to the repository.
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.
- 2mo ago First seen · 45 lines · 351 tokens per session scan A e072fda150e8
cursorrules is a cursor rule published in the GitHub repository mckinsey/agents-at-scale-ark (434 stars, last pushed yesterday), licensed Apache-2.0. It adds 351 tokens to every session, about $0.0014 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 2026-09-03.
cursorrules compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cursorrulesmckinsey/agents-at-scale-ark | Cursor rule | 434 | yesterday | Apache-2.0 | A | 351 | Cursor |
| changelogOrlojHQ/orloj | Cursor rule | 126 | 7d ago | Apache-2.0 | A | 196 | Cursor |
| git-authorRyanAlberts/best-of-Agent-Harnesses | Cursor rule | 1.5k | 3d ago | CC-BY-SA-4.0 | A | 235 | Cursor |
| gitChatbotXIO/ChatbotX | Cursor rule | 1.1k | today | none | A | 29 | Cursor |
| savevictusfate/scaffold | Cursor rule | 7 | 2d ago | MIT | A | 88 | Cursor |
| git-commitkyungseo/ai-workflow-harness | Cursor rule | 14 | 3mo ago | Apache-2.0 | A | 18 | Cursor |
| 04-review-and-commitpueraeternis/agentic-project-template | Cursor rule | 2 | 4mo ago | MIT | A | 546 | Cursor |