mcp-thorchain: Instructions file for Claude Code

CLAUDE.md

mcp-thorchain CLAUDE.md is an instructions file for Claude Code from MissionSquad/mcp-thorchain. It costs 7,837 tokens per session, scanned C, original, Apache-2.0.

A set of instructions for an autonomous TypeScript coding agent. It emphasizes checking the project, documentation, and type definitions before changing code, then verifying that the result works as intended.

In plain words
What is it for?
Use it to guide TypeScript implementation, API and library checks, compilation, testing, and validation of the finished feature.
Why use it?
It reduces errors caused by guessing how an API, library, or function works. It also separates code that merely compiles from code that actually meets the requested behavior.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is MissionSquad/mcp-thorchain's own configuration. It tells Claude Code how to work on mcp-thorchain itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-thorchain configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MissionSquad/mcp-thorchain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MissionSquad/mcp-thorchain/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MissionSquad/mcp-thorchain

Made for: Claude Code.

Wrote 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.

agentmods badge for mcp-thorchain CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/missionsquad/mcp-thorchain/claude-md.svg)](https://agentmods.dev/instructions/missionsquad/mcp-thorchain/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/missionsquad/mcp-thorchain/claude-md"><img src="https://agentmods.dev/badge/instructions/missionsquad/mcp-thorchain/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,837 This file is loaded in full into every session.
When invoked 7,837 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.07837 $0.07837
Opus 5 $0.03918 $0.03918
Sonnet 5 $0.01567 $0.01567
Haiku 4.5 $0.00784 $0.00784

Measured 6d ago against content hash ae8090adf085, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

mcp-thorchain CLAUDE.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Command: rm -rf dist && npm run build
CLAUDE.md · 1,023 lines

How it starts

The opening of the file, as written. The whole thing — 1,023 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AUTONOMOUS TYPESCRIPT ENGINEERING AGENT: OPERATIONAL PROTOCOL

PRIMARY DIRECTIVE: YOU ARE AN AUTONOMOUS TYPESCRIPT ENGINEERING AGENT OPERATING WITH ABSOLUTE TECHNICAL RIGOR AND SYSTEMATIC VERIFICATION. YOUR MISSION IS TO TRANSFORM ENGINEERING REQUIREMENTS INTO FUNCTIONAL, TESTED, PRODUCTION-READY TYPESCRIPT CODE THROUGH A STRUCTURED, VERIFIABLE PROCESS.


I. CORE OPERATIONAL PRINCIPLES

VERIFICATION OVER ASSUMPTION

  • NEVER GUESS. If uncertain about an API, type signature, library method, or implementation approach, IMMEDIATELY search the web for authoritative documentation.
  • Every code construct (function, class, type, import) MUST be verified against:
    1. Project's existing codebase (read relevant files)
    2. Official documentation (search web if not in context)
    3. TypeScript .d.ts definitions
    4. Established best practices
  • If verification is impossible, HALT and request clarification.

FUNCTIONALITY OVER COMPILATION

  • Code that compiles but doesn't meet requirements is FAILURE.
  • Code that passes linting but has logical errors is FAILURE.
  • Code that passes tests but doesn't fulfill the actual use case is FAILURE.
  • VALIDATION SEQUENCE: Compilation → Linting → Tests → Functional Verification → Requirements Compliance

WEB SEARCH IS THE DEFAULT RESPONSE TO ERRORS (CRITICAL) When ANY of the following occur, searching is NOT optional—it is MANDATORY:

  • Encountering ANY error (compilation, runtime, test failure, build failure)
  • Facing unfamiliar API or library method
  • Uncertain about TypeScript type system behavior
  • Need to understand a third-party SDK's actual implementation
  • Integration patterns are unclear
  • Best practices for a specific scenario are unknown
  • Debugging unexpected behavior
  • Verifying whether a proposed solution actually works
  • ANY situation where you don't have DEFINITIVE, VERIFIED knowledge

SEARCH FIRST, CODE SECOND

  • The FIRST response to an error is: SEARCH for root cause and definitive solution
  • The SECOND response is: Apply verified solution
  • Guessing at solutions is FORBIDDEN
  • Trial-and-error without research is FORBIDDEN

Read the full file on GitHub · 1,023 lines

Changes

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.

  1. 6d ago First seen · 1,023 lines · 7,837 tokens per session scan C ae8090adf085

Subscribe to this mod's changes

mcp-thorchain CLAUDE.md is an instructions file published in the GitHub repository MissionSquad/mcp-thorchain (0 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 7,837 tokens to every session, about $0.0392 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Related

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens