Borrowing it
Nothing to install: this file belongs to slettmayer/calc-mcp-server. 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/slettmayer/calc-mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/slettmayer/calc-mcp-serverWrote 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/slettmayer/calc-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/slettmayer/calc-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/slettmayer/calc-mcp-server/agents-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 | $0.01658 | $0.01658 |
| Opus 5 | $0.00829 | $0.00829 |
| Sonnet 5 | $0.00332 | $0.00332 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
calc-mcp-server AGENTS.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 6d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Calculator MCP Server
MCP server for exact arithmetic, usable by LLMs via the Model Context Protocol. One
calculatetool over a hand-rolled AST allowlist — noeval(), no unbounded dependencies.
Editing this guide:
AGENTS.mdis the single source of truth for project context, read by all AI coding agents and humans. Keep it concise — put detail indocs/and link it. When you change code that alters documented behavior, update the matchingdocs/file in the same PR — nothing automated checks this, so it rests on whoever writes the change (see docs/README.md).
Quick Reference
- Lint:
ruff check . - Format:
ruff format . - Test:
pytest tests/ -v - Run server:
uvx --from . calc-mcp-serverorpython -m calc_mcp_server.server - Validate (CI): Ruff + pytest (all must pass via the
gatejob) - Release: run the Auto Release workflow; the version comes from the git tag -- see RELEASING.md
Where to Find Things
| I need to... | Read |
|---|---|
| Understand the architecture | ARCHITECTURE.md |
| Change the allowlist, a cap, or anything security-relevant | SAFE-EVALUATION.md |
| Write code that fits conventions | CONVENTIONS.md |
| Know the tech stack | TECH-STACK.md |
| Write or run tests | TESTING.md |
| Cut a release, or add a changelog entry | RELEASING.md |
| Understand the domain and why this repo exists | OVERVIEW.md |
Architecture Overview
MCP presentation layer over a pure, dependency-free evaluator. Purely functional — no classes outside
the MCPServer instance and the exception hierarchy. All code lives in src/calc_mcp_server/.
server.py-- MCPServer tool registration (1 tool), stdio entry point, turnsCalculatorErrorinto anError:lineevaluator.py-- parses, walks the AST against the allowlist, enforces the caps, renders the resultconst.py-- operator aliases, name/function allowlists, the four caps, float precision
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.
- 6d ago First seen · 98 lines · 1,658 tokens per session scan A e6dd5111a00a
calc-mcp-server AGENTS.md is an instructions file published in the GitHub repository slettmayer/calc-mcp-server (0 stars, last pushed 3d ago), licensed MIT. It adds 1,658 tokens to every session, about $0.0083 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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).
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.