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/syrin-labs/cli/claude-mdgit clone --depth 1 https://github.com/syrin-labs/cliWhat 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 | $0.03200 | $0.03200 |
| Opus 5 | $0.01600 | $0.01600 |
| Sonnet 5 | $0.00640 | $0.00640 |
| Haiku 4.5 | $0.00320 | $0.00320 |
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.
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 configurationdoctor: Validate configuration and environmentdev: Interactive LLM-MCP development environmenttest: Contract-based tool testing with sandboxinganalyse: Static validation of MCP tool contractslist: Inspect tools, resources, and promptsconfig: Manage local/global configurationupdate/rollback: Version management
All commands use unified error handling via command-error-handler.ts.
2. Configuration Management (/config)
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.
- 2d ago First seen · 452 lines · 3,200 tokens per session scan A ee019b236542
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.
Other instructions, from other repositories
keynobi AGENTS.md
Instructions for thiagodmont/keynobi, covering agent instructions, tech stack, before you write code, key rules and testing instructions.
django-orbit CLAUDE.md
Instructions for astro-stack/django-orbit, covering claude.md, what this is, commands, install in editable mode with dev dependencies and run all tests.
mcp-dap-server CLAUDE.md
Instructions for go-delve/mcp-dap-server, covering claude.md, project overview, architecture, core components and key patterns.
liferay-dummy-factory CLAUDE.md
Instructions for yasuflatland-lf/liferay-dummy-factory, covering liferay-dummy-factory, where to find concrete details and history, core contracts — break these and things go silently wrong and common gradle commands.
crashdx CLAUDE.md
Instructions for r00tify/crashdx, covering claude.md, commands, architecture, diagnosis engine and non-obvious data constraints.
Proxyfan copilot-instructions.md
Instructions for Proxyfan/Proxyfan, covering copilot instructions — proxyfan, quality bar, development environment, build & test and full debug build with restore.