cursorrules

A set of project rules for developing the llm-cli-gateway MCP server, including naming, errors, logging, validation, retries, and tests.

In plain words
What is it for?
Guiding new tools, error handling, TypeScript types, Zod input validation, retry logic, circuit breakers, logging, and unit and integration tests.
Why use it?
It keeps changes consistent with the server's existing conventions and reduces avoidable integration and maintenance problems.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/verivus-oss/llm-cli-gateway/cursorrules
Clone the repo
git clone --depth 1 https://github.com/verivus-oss/llm-cli-gateway

Made for: Cursor.

Per session 398 This file is loaded in full into every session.
When invoked 398 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00398 $0.00398
Opus 5 $0.00199 $0.00199
Sonnet 5 $0.00080 $0.00080
Haiku 4.5 $0.00040 $0.00040

Measured 2d ago against content hash 649042e3868d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.cursorrules · 44 lines

What it actually says

You are working on the llm-cli-gateway MCP server.

CRITICAL: Before making ANY changes to this codebase:

  1. Read docs/guides/BEST_PRACTICES.md
  2. Follow ALL conventions outlined in docs/guides/BEST_PRACTICES.md

Key Rules:

  • Tool names MUST use snake_case (e.g., claude_request, not claudeRequest)
  • Error messages MUST be actionable, not just "not found"
  • Logging MUST go to stderr, never stdout (MCP protocol uses stdout)
  • All exported functions MUST have TypeScript return types
  • Session state MUST be minimal - only IDs and metadata
  • Circuit breaker state MUST be respected in retry logic
  • Tests MUST be added for any new functionality
  • DRY principle - no duplicate constants or logic

When adding new tools:

  1. Use Zod for input validation
  2. Provide clear descriptions (20+ chars with action words)
  3. Return structured error responses via createErrorResponse()
  4. Add unit AND integration tests
  5. Update docs/guides/BEST_PRACTICES.md if introducing new patterns

When adding retry/resilience logic:

  1. Always add jitter to exponential backoff
  2. Ensure operations are idempotent
  3. Use appropriate circuit breaker
  4. Log retry attempts with context

Test Requirements:

  • Enforced coverage: 70% lines, functions, and statements; 60% branches
  • Both unit tests (isolation) and integration tests (real calls)
  • Follow AAA pattern (Arrange, Act, Assert)

Self-Check Before Finalizing Changes: □ All tool names use snake_case □ Error messages are actionable and context-aware □ No console.log (use logger.info/error/debug) □ All exported functions have return type annotations □ Tests added for new functionality □ TypeScript compiles: npm run build □ All tests pass: npm test □ No duplicate code or constants

Changes

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.

  1. 2d ago First seen · 44 lines · 398 tokens per session scan A 649042e3868d

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository verivus-oss/llm-cli-gateway (14 stars, last pushed 8d ago), licensed MIT. It adds 398 tokens to every session, about $0.0020 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.