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 instructions/islobodan/cruncher-mcp/agents-mdgit clone --depth 1 https://github.com/islobodan/cruncher-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/islobodan/cruncher-mcp/agents-md)<a href="https://agentmods.dev/instructions/islobodan/cruncher-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/islobodan/cruncher-mcp/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 | $0.01968 | $0.01968 |
| Opus 5 | $0.00984 | $0.00984 |
| Sonnet 5 | $0.00394 | $0.00394 |
| Haiku 4.5 | $0.00197 | $0.00197 |
Grade A, and why
cruncher-mcp 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 4d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for Cruncher (MCP Server)
You are connected to Cruncher, a highly reliable, accurate, and zero-dependency scientific calculator built over the Model Context Protocol (MCP).
Whenever a user asks you to perform mathematics, statistics, unit conversions, or fetch physical constants, you must use the tools provided by Cruncher rather than relying on your own internal mental math or generating a Python script, as Cruncher guarantees zero hallucination, strict decimal accuracy, and infinite-loop protection.
Server Overview
| Attribute | Value |
|---|---|
| Version | v1.2.31 |
| Total Tools | 43 (full), 34 (standard default), 5 (minimal) |
| Default Tier | standard (34 tools) |
| Protocol Version | 2025-11-25 (latest MCP spec) |
| Timeout | 3 seconds (configurable via CRUNCHER_TIMEOUT env var) |
| Dependencies | Zero (pure Node.js) |
1. Prioritize evaluate_expression for Math
For any non-trivial math, use one call to evaluate_expression instead of chaining individual tools.
Supported in Expression Strings
| Category | Items |
|---|---|
| Operators | +, -, *, /, %, ^ (power) |
| Constants | pi, e, tau, phi, sqrt2, euler_mascheroni, c, g, G, h, k, R, NA, e_charge, m_e, m_p |
| Trig | sin(), cos(), tan(), asin(), acos(), atan() |
| Math | sqrt(), log10(), ln(), log(x, base), abs(), round(), floor(), ceil(), min(), max() |
Examples
evaluate_expression("2 * pi * 5")
evaluate_expression("sin(pi/6) + sqrt(16)")
evaluate_expression("3^3 + abs(-5) / 2")
evaluate_expression("log10(1000) ^ 2")
evaluate_expression("log(16, 2)")
evaluate_expression("1e6 + 2.5e-3")
Constraints
- Letters are only allowed for the constants and function names listed above — no algebraic variables like
x + 2 - Individual trig tool calls (
sine,cosine, etc.) use the global angle mode (default: degrees).evaluate_expressionalways uses radians (JavaScript standard). - Scientific notation:
1e6,2.5e-3both work - Explicit operators required:
2 * piworks,2pidoes not
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.
- 4d ago First seen · 197 lines · 1,968 tokens per session scan A 8f4ca9306f5d
cruncher-mcp AGENTS.md is an instructions file published in the GitHub repository islobodan/cruncher-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,968 tokens to every session, about $0.0098 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
SutroYaro GEMINI.md
Instructions for cybertronai/SutroYaro, covering gemini.md - sutro group research workspace, project context, read these first, core concepts and current best methods.
braina GEMINI.md
Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.
cdxml-toolkit-community AGENTS.md
AGENTS.md instructions for ZiChenWang114514/cdxml-toolkit-community, a project described as: Community CDXML toolkit and MCP server.
research-automation CLAUDE.md
Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.
shannon-prover CLAUDE.md
Claude Code instructions for SkyShannonProver/shannon-prover, covering shannon prover: claude entry point, current boundary, easycrypt environment, eval safety and current documentation.
SciCrucible CLAUDE.md
Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.