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/brookstalley/cordyceps/claude-mdgit clone --depth 1 https://github.com/brookstalley/cordycepsWrote 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/brookstalley/cordyceps/claude-md)<a href="https://agentmods.dev/instructions/brookstalley/cordyceps/claude-md"><img src="https://agentmods.dev/badge/instructions/brookstalley/cordyceps/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 | $0.02892 | $0.02892 |
| Opus 5 | $0.01446 | $0.01446 |
| Sonnet 5 | $0.00578 | $0.00578 |
| Haiku 4.5 | $0.00289 | $0.00289 |
Grade A, and why
cordyceps 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 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Cordyceps is a Grasshopper plugin that exposes Grasshopper and Rhino functionality via the Model Context Protocol (MCP). It allows AI assistants to programmatically control Grasshopper (adding components, creating connections, configuring scripts) and Rhino (managing objects, layers, materials, rendering).
Build Commands
# Build the plugin (Release configuration required)
dotnet build src/Cordyceps/Cordyceps.csproj -c Release
# The built .gha file is automatically copied to releases/ (gitignored - a build output)
The project targets .NET 8.0 and outputs a Grasshopper plugin (.gha file). Debug builds are blocked—always use -c Release.
Architecture
Core Components
McpServer.cs - HTTP/SSE server implementing the MCP protocol. Listens on a configurable port (default 26929), handles JSON-RPC requests, and manages SSE sessions for streaming responses. Discovers tools via reflection using [McpServerToolType] and [McpServerTool] attributes.
CordycepsComponent.cs - The Grasshopper component that users drop on the canvas. Manages the MCP server lifecycle - starts the server when placed, stops when removed. Outputs server status and last command received.
Core/GrasshopperContext.cs - Thread-safe wrapper for Grasshopper document access. All Grasshopper operations must run on the UI thread; this class provides ExecuteOnUiThread() methods that marshal calls correctly.
Core/ComponentRegistry.cs - Resolves component type names to actual Grasshopper components. Handles aliases (e.g., "python" -> "Python 3 Script") and supports creation by name or GUID.
Core/UnifiedToolHelpers.cs - Shared utilities for the unified tool architecture including action dispatch, help generation, and standardized response formatting.
Core/ToolHelpers.cs - Shared document/component utilities used across every tool: active-document and component resolution (by GUID or name), protected/infrastructure-id checks, cluster-safe recompute, component-info builders, JSON (de)serialization helpers, and SuccessResponse/ErrorResponse formatting.
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 · 210 lines · 2,892 tokens per session scan A c7b692ce360f
cordyceps CLAUDE.md is an instructions file published in the GitHub repository brookstalley/cordyceps (96 stars, last pushed 7d ago), licensed MIT. It adds 2,892 tokens to every session, about $0.0145 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
semio AGENTS.md
AGENTS.md instructions for usalu/semio, a project described as: 💻 The right operating system for the left brain 🧠.
semio CLAUDE.md
Claude Code instructions for usalu/semio, a project described as: 💻 The right operating system for the left brain 🧠.
semio GEMINI.md
Gemini CLI instructions for usalu/semio, a project described as: 💻 The right operating system for the left brain 🧠.
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).
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 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).