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/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/rules/boxels/cursor-rules/documentation)<a href="https://agentmods.dev/rules/boxels/cursor-rules/documentation"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/documentation/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/boxels/cursor-rules/documentation"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/documentation.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 | $0.00474 | $0.00474 |
| Opus 5 | $0.00237 | $0.00237 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
documentation 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 yesterday.
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
Documentation Rules
Always keep docs current
- After any feature, architecture change, or removal: update relevant docs and
.cursor/rulesto match reality. Do not leave stale or contradictory documentation. - Prefer editing existing docs over creating duplicates. Search the doc folder before writing a new file.
- What to document: architecture decisions, removed/deprecated patterns, new conventions, critical constraints (things agents must NOT do), and cross-references between docs and rules.
Doc location and naming
- Agent-facing reference docs live in [doc folder, e.g. "docs/"].
- Naming: [convention, e.g. "FEATURE_NAME.md in ALL_CAPS_WITH_UNDERSCORES", "kebab-case.md"]. Keep one convention and stick to it.
- New feature docs should include: one-sentence purpose, files/routes/tables touched, how it works, critical constraints, and links to related docs.
Cursor rules maintenance
- If a change affects patterns or conventions other agents need, update
.cursor/rules/as well as prose docs. - Cross-cutting concerns → [global rules file, e.g. "global-rules.mdc"]. Domain-specific guidance → the matching rule file (tech, design, security, models, etc.) or a new focused rule file. New rule files must use the
.mdcextension. - Add a one-line "see
docs/FOO.md" pointer from rules when a longer reference exists. - Model names in
models.mdcgo stale every few months. When updating docs after a Cursor model change, refresh that file against cursor.com/docs/models.
Trigger: "update docs"
When the user says "update documentation", "update docs", "update the docs", or similar, run the update-docs skill (.cursor/skills/update-docs/SKILL.md). It defines the full find → edit → create-if-needed → cross-reference → report workflow. Don't ask which files to update — the skill finds them.
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.
- yesterday First seen · 31 lines · 474 tokens per session scan A e440529ef134
documentation is a cursor rule published in the GitHub repository BOXELS/cursor-rules (6 stars, last pushed yesterday), licensed MIT. It adds 474 tokens to every session, about $0.0024 per session on Opus 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.