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/nedcodes-ok/cursor-doctor/trpcgit clone --depth 1 https://github.com/nedcodes-ok/cursor-doctorWhat 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 | $0.00000 | $0.00311 |
| Opus 5 | $0.00000 | $0.00156 |
| Sonnet 5 | $0.00000 | $0.00062 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
trpc 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
tRPC Rules
Router Setup
- Organize routers by domain (userRouter, postRouter, etc.) and merge with appRouter
- Keep procedure definitions focused — one operation per procedure
- Use input validation with zod schemas on every procedure
- Define output types explicitly when the inferred type is complex
Procedures
- Use query for read operations, mutation for writes
- Use middleware for cross-cutting concerns (auth, logging, rate limiting)
- Protect procedures with authentication middleware, not inline checks
- Keep business logic in separate service functions, not directly in procedures
Client Usage
- Use the generated typed client — never call procedures with untyped fetch
- Handle loading and error states for every query (isLoading, isError)
- Use optimistic updates for mutations that modify displayed data
- Invalidate related queries after mutations using utils.queryKey.invalidate()
Error Handling
- Throw TRPCError with appropriate codes (UNAUTHORIZED, NOT_FOUND, BAD_REQUEST)
- Do not expose internal error details to the client — map to user-friendly messages
- Log full error details server-side
Anti-patterns
- Do not create one giant router — split by domain
- Do not skip input validation — every procedure needs a zod schema
- Do not mix tRPC calls with raw fetch to the same endpoints
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 · 35 lines · 311 tokens per session scan A 84497931e077
trpc is a cursor rule published in the GitHub repository nedcodes-ok/cursor-doctor (9 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 311 tokens. 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 cursor rules, from other repositories
java
Modern Java: records, sealed classes, streams, virtual threads.
javascript
Modern JavaScript: ES2023+, async patterns, common traps.
accessibility
Accessibility: semantic HTML, ARIA, keyboard navigation, testing.
cross-tool-config
Cross-tool AI config: what transfers between Cursor, Claude Code, Copilot, Windsurf, Gemini, and Codex.
angular
Angular: signals, standalone components, RxJS patterns.
django
Django: models, views, ORM best practices.