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 agentmods add rules/smythos/smythos-studio/cursorrulesgit clone --depth 1 https://github.com/SmythOS/smythos-studioWhat 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 | $0.00255 | $0.00255 |
| Opus 5 | $0.00128 | $0.00128 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00026 | $0.00026 |
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 2d 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
OPERATIONAL FEATURES
- Context Window Warnings: Alert the user when nearing the context window limit.
- Missing Content Requests: Request the user to provide project code, documentation, or definitions necessary for an adequate response.
- Error Correction: Indicate all user prompt errors of terminology, convention, or understanding, regardless of their relevance to the user prompt.
CRITICALLY IMPORTANT RULES
- Completeness: Generate full code, no placeholders. If unable, explain in comments.
- Comments: Include clear inline comments and JSDoc headers describing each step of code.
- Error Checking: Implement error checking and type validation.
- Types: Implement strict TypeScript notation, defining new types as necessary. Additionally:
- Do not use the 'any' type.
- Do not use the non-null assertion operator (
!). - Do not cast to unknown (e.g.
as unknown as T).
- Strings: Adhere to these standards for strings:
- Use single quotes (
') for strings. - Use string templates instead of operational concatenation.
- Use single quotes (
It is critically important that you adhere to the above five rules.
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.
- 2d ago First seen · 18 lines · 255 tokens per session scan A 24b4bd1b10bf
cursorrules is a cursor rule published in the GitHub repository SmythOS/smythos-studio (295 stars, last pushed 5mo ago), licensed MIT. It adds 255 tokens to every session, about $0.0013 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 2026-08-30.
Other cursor rules, from other repositories
write
Writing style guide with AI detection avoidance. For tweets, LinkedIn, blogs, READMEs, commits. Activate with @write.
ehs-ims-conventions
EHS IMS app — RBAC, data layer, tRPC, migrations, AI boundaries.
php-types-validation
Guidelines for type definitions and validation in PHP MCP SDK.
php-client-implementation
Guidelines for implementing MCP clients in PHP.
cursorrules
When the user asks about meok cra annex iv classifier, use meok-cra-annex-iv-classifier-mcp tools: classifyproduct, auditessentialrequirements, generatedoctemplate, signclassificationcert.
readme-best-practices
README Best Practices - enforces high-quality README patterns when creating or editing README files.