cclsp CLAUDE.md

cclsp CLAUDE.md is an instructions file for Claude Code from ktnyt/cclsp. It costs 1,391 tokens per session, scanned A, original, MIT.

Repository instructions for Claude Code, describing the cclsp project and its commands. cclsp connects language-server features such as finding definitions and references to an AI tool interface.

In plain words
What is it for?
Use it when working on cclsp, especially when running development, build, setup, lint, formatting, type-checking, or test commands.
Why use it?
It gives the coding agent the project context and the exact commands for installing, developing, checking, testing, and building the code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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/ktnyt/cclsp/claude-md
Clone the repo
git clone --depth 1 https://github.com/ktnyt/cclsp

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 cclsp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ktnyt/cclsp/claude-md.svg)](https://agentmods.dev/instructions/ktnyt/cclsp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ktnyt/cclsp/claude-md"><img src="https://agentmods.dev/badge/instructions/ktnyt/cclsp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,391 This file is loaded in full into every session.
When invoked 1,391 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 5.1 $0.01391 $0.01391
Opus 5 $0.00696 $0.00696
Sonnet 5 $0.00278 $0.00278
Haiku 4.5 $0.00139 $0.00139

Measured 6d ago against content hash 6ff949b42a36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

cclsp 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.

CLAUDE.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 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

cclsp is an MCP (Model Context Protocol) server that bridges Language Server Protocol (LSP) functionality to MCP tools. It allows MCP clients to access LSP features like "go to definition" and "find references" through a standardized interface.

Development Commands

# Install dependencies
bun install

# Development with hot reload
bun run dev

# Build for production
bun run build

# Run the built server
bun run start
# or directly
node dist/index.js

# Run setup wizard to configure LSP servers
cclsp setup

# Quality assurance
bun run lint         # Check code style and issues
bun run lint:fix     # Auto-fix safe issues
bun run format       # Format code with Biome
bun run typecheck    # Run TypeScript type checking
bun run test         # Run unit tests
bun run test:manual  # Run manual MCP client test

# Full pre-publish check
npm run prepublishOnly  # build + test + typecheck

Architecture

Core Components

MCP Server Layer (index.ts)

  • Entry point that implements MCP protocol
  • Exposes find_definition, find_references, and rename_symbol tools
  • Handles MCP client requests and delegates to LSP layer
  • Includes subcommand handling for cclsp setup

LSP Client Layer (src/lsp-client.ts)

  • Manages multiple LSP server processes concurrently
  • Handles LSP protocol communication (JSON-RPC over stdio)
  • Maps file extensions to appropriate language servers
  • Maintains process lifecycle and request/response correlation
  • Auto-detects and applies server-specific adapters

Server Adapter System (src/lsp/adapters/)

  • Built-in adapters for LSP servers with non-standard behavior
  • Vue Language Server adapter handles custom tsserver/request protocol
  • Pyright adapter provides extended timeouts for large projects
  • Automatically detected based on server command (no configuration needed)
  • Internal use only - not user-extensible

Read the full file on GitHub · 192 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 · 192 lines · 1,391 tokens per session scan A 6ff949b42a36

Subscribe to this mod's changes

cclsp CLAUDE.md is an instructions file published in the GitHub repository ktnyt/cclsp (674 stars, last pushed 6mo ago), licensed MIT. It adds 1,391 tokens to every session, about $0.0070 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.