Borrowing it
Nothing to install: this file belongs to coo-quack/calc-mcp. 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/coo-quack/calc-mcp/develop/CLAUDE.mdgit clone --depth 1 https://github.com/coo-quack/calc-mcpWrote 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/coo-quack/calc-mcp/claude-md)<a href="https://agentmods.dev/instructions/coo-quack/calc-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/coo-quack/calc-mcp/claude-md/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/instructions/coo-quack/calc-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/coo-quack/calc-mcp/claude-md.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 | $0.01417 | $0.01417 |
| Opus 5.5 | $0.00567 | $0.00567 |
| Sonnet 5.5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
calc-mcp 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 2mo 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Rules
Overview
MCP (Model Context Protocol) server providing 21 tools for calculations and operations that LLMs struggle with. Published as @coo-quack/calc-mcp on npm.
Tech Stack
- Runtime: Bun
- Language: TypeScript (strict mode)
- Linter/Formatter: Biome (2-space indentation)
- Docs: VitePress (
docs/) - Dependencies:
@modelcontextprotocol/sdk,zod,mathjs,date-fns
Commands
bun test— Run all testsbun run build— Build for production (minify + sourcemap + shebang)bun run lint— Biome checkbun run format— Biome formatbun run dev— Start dev serverbun run docs:dev— VitePress dev server
Project Structure
src/index.ts # MCP server entry, tool registration
src/tools/*.ts # 21 tool modules (one file per tool)
tests/tools/*.test.ts # Unit tests (one file per tool)
tests/e2e/ # E2E tests (Node.js test runner via MCP protocol)
docs/ # VitePress documentation site
Tool Architecture
Every tool follows the same pattern:
import { z } from "zod";
import type { ToolDefinition } from "../index.js";
const schema = {
param: z.string().describe("Description"),
};
const inputSchema = z.object(schema);
type Input = z.infer<typeof inputSchema>;
export function execute(input: Input): string {
// Pure business logic, returns string (JSON or plain text)
}
export const tool: ToolDefinition = {
name: "tool_name", // snake_case
description: "LLM-facing description",
schema, // NOT inputSchema
handler: async (args: Record<string, unknown>) => {
const input = inputSchema.parse(args);
return execute(input);
},
};
Registration: import in src/index.ts → add to tools array.
Adding a New Tool
- Create
src/tools/<name>.ts— exportexecute()andtool - Create
tests/tools/<name>.test.ts— testexecute()directly - Register in
src/index.ts— import and add totoolsarray - Update docs:
README.md,docs/tools.md,docs/examples.md
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.
- 2mo ago First seen · 161 lines · 1,417 tokens per session scan A 678f27afa435
calc-mcp CLAUDE.md is an instructions file published in the GitHub repository coo-quack/calc-mcp (9 stars, last pushed yesterday), licensed MIT. It adds 1,417 tokens to every session, about $0.0057 per session on Opus 5.5. 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 2026-08-31.
calc-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| calc-mcp CLAUDE.mdcoo-quack/calc-mcp | Instructions file | 9 | yesterday | MIT | A | 1,417 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |