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/ktnyt/cclsp/claude-mdgit clone --depth 1 https://github.com/ktnyt/cclspWrote 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/ktnyt/cclsp/claude-md)<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>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 | $0.01391 | $0.01391 |
| Opus 5 | $0.00696 | $0.00696 |
| Sonnet 5 | $0.00278 | $0.00278 |
| Haiku 4.5 | $0.00139 | $0.00139 |
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.
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, andrename_symboltools - 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/requestprotocol - Pyright adapter provides extended timeouts for large projects
- Automatically detected based on server command (no configuration needed)
- Internal use only - not user-extensible
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 · 192 lines · 1,391 tokens per session scan A 6ff949b42a36
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.
Other instructions, from other repositories
nvim-mcp CLAUDE.md
Claude Code instructions for linw1995/nvim-mcp, covering claude.md, project overview, development commands, building and running and development build and run.
chromia-lsp-mcp CLAUDE.md
Claude Code instructions for ChromiaProject/chromia-lsp-mcp, covering claude.md, what this is, commands, architecture and adding a tool.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).