Borrowing it
Nothing to install: this file belongs to gokr/nimcp. 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/gokr/nimcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/gokr/nimcpWrote 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/instructions/gokr/nimcp/claude-md)<a href="https://agentmods.dev/instructions/gokr/nimcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gokr/nimcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.01143 | $0.01143 |
| Opus 5 | $0.00571 | $0.00571 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
nimcp CLAUDE.md 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
NimCP - Nim library for MCP servers using macro-based APIs. Implements JSON-RPC 2.0 over stdio/websockets/SSE for LLM integration.
Commands
nimble test # Run all tests
nim r tests/test_*.nim # Run specific test
nim c examples/ # Build examples
nimble docs # Generate docs
nim c -r examples/basic_calculator.nim # Compile and run example
Architecture
Core: types.nim (MCP types), server.nim (server separate from transports), mcpmacros.nim (macro API), protocol.nim (JSON-RPC)
Macro API (recommended) can be seen in @examples/macro_calculator.nim
The macro API automatically extracts:
- Tool names from proc names
- Descriptions from doc comments (first line)
- JSON schemas from parameter types (int, float, string, bool, seq)
- Parameter documentation from doc comment parameter lists
- Type-safe wrappers for JSON parameter conversion
Key types: McpServer, McpTool, McpResource, McpPrompt, McpRequestContext
Transports: Stdio (CLI), HTTP (REST), WebSocket (realtime), SSE (deprecated)
Examples: See examples/ - calculator variants for each transport
Dependencies: nim >= 2.2.4, mummy, taskpools
MCP specification
Streamable HTTP
- https://modelcontextprotocol.io/specification/2025-06-18/basic/transports#streamable-http
- https://www.claudemcp.com/blog/mcp-streamable-http
- https://mcp-framework.com/docs/Transports/http-stream-transport
Coding Guidelines
- Do not shadow the local
resultvariable (Nim built-in) - Doc comments:
##below proc signature - Prefer generics or object variants over methods
- Use
return expressionfor early exits - Prefer direct field access over getters/setters
- JSON: Use
%*{}syntax - NO
asyncdispatch- usetaskpoolsfor concurrency or normal threading - Remove old code during refactoring
- Import full modules, not select symbols
- Use
*to export fields that should be publicly accessible - If something is not exported, export it instead of doing workarounds
- Do not be afraid to break backwards compatibility
- Do not add comments talking about how good something is, it is just noise. Be brief.
- Do not add comments that reflect what has changed, we use git for change tracking, only describe current code
- Do not add unnecessary commentary or explain code that is self-explanatory
- Single-line functions: Use direct expression without
result =assignment orreturnstatement - Multi-line functions: Use
result =assignment andreturnstatement for clarity - Early exits: Use
return valueinstead ofresult = value; return - Exception handlers: Use
return expressionfor error cases - JSON Object Construction: Prefer the
%*{}syntax for clean, readable JSON creation - Content Serialization: Use centralized utilities for consistent formatting
- Error Response Creation: Use standardized error utilities across all transport layers
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.
- 7d ago First seen · 115 lines · 1,143 tokens per session scan A 137448fb621d
nimcp CLAUDE.md is an instructions file published in the GitHub repository gokr/nimcp (24 stars, last pushed 7mo ago), licensed MIT. It adds 1,143 tokens to every session, about $0.0057 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.