cli CLAUDE.md

Development instructions for Syrin, a command-line tool for checking and testing MCP servers before they are deployed. MCP is a standard way for software tools to expose capabilities to AI assistants.

In plain words
What is it for?
Use them when running Syrin locally, testing MCP server behavior, checking code quality, or preparing a release.
Why use it?
They collect the commands and checks needed to build, run, test, lint, format, type-check, and publish the project.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/syrin-labs/cli/claude-md
Clone the repo
git clone --depth 1 https://github.com/syrin-labs/cli
Per session 3,200 This file is loaded in full into every session.
When invoked 3,200 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03200 $0.03200
Opus 5 $0.01600 $0.01600
Sonnet 5 $0.00640 $0.00640
Haiku 4.5 $0.00320 $0.00320

Measured 2d ago against content hash ee019b236542, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli 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 2d 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.

CLAUDE.md · 452 lines

How it starts

The opening of the file, as written. The whole thing — 452 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

Syrin is a runtime intelligence system for MCP (Model Context Protocol) servers. It helps developers validate, test, and reason about MCP execution before production deployment through static analysis, contract-based testing, and interactive development environments.

Development Commands

Building and Running

# Build the project (TypeScript compilation + path alias resolution + template copy)
npm run build

# Run Syrin CLI locally (rebuilds and executes)
npm run syrin <command>

# Example: Run dev mode locally
npm run syrin dev --exec

Testing

# Run all tests (watch mode)
npm test

# Run tests once
npm run test:run

# Run tests with coverage
npm run test:coverage

# Run tests with UI
npm run test:ui

# Run specific test file
npm test -- src/runtime/dev/session.test.ts

Code Quality

# Lint the codebase
npm run lint

# Lint and fix issues
npm run lint:fix

# Format code (Prettier)
npm run format

# Check formatting
npm run format:check

# Type check without building
npm run type-check

Publishing

# Prepare for publish (runs build automatically)
npm run prepublishOnly

High-Level Architecture

Syrin uses a layered, event-driven architecture with five primary layers:

1. CLI Command Layer (/cli)

Entry point using Commander.js. Commands map to handlers that orchestrate lower layers:

  • init: Initialize project configuration
  • doctor: Validate configuration and environment
  • dev: Interactive LLM-MCP development environment
  • test: Contract-based tool testing with sandboxing
  • analyse: Static validation of MCP tool contracts
  • list: Inspect tools, resources, and prompts
  • config: Manage local/global configuration
  • update/rollback: Version management

All commands use unified error handling via command-error-handler.ts.

2. Configuration Management (/config)

Read the full file on GitHub · 452 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. 2d ago First seen · 452 lines · 3,200 tokens per session scan A ee019b236542

Subscribe to this mod's changes

cli CLAUDE.md is an instructions file published in the GitHub repository syrin-labs/cli (48 stars, last pushed 6mo ago), licensed ISC. It adds 3,200 tokens to every session, about $0.0160 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.