Borrowing it
Nothing to install: this file belongs to karellen/karellen-lsp-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/karellen/karellen-lsp-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/karellen/karellen-lsp-mcpWrote 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/karellen/karellen-lsp-mcp/claude-md)<a href="https://agentmods.dev/instructions/karellen/karellen-lsp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/karellen/karellen-lsp-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/karellen/karellen-lsp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/karellen/karellen-lsp-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01791 | $0.01791 |
| Opus 5.5 | $0.00716 | $0.00716 |
| Sonnet 5.5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
karellen-lsp-mcp 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 16d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: karellen-lsp-mcp
MCP server bridging to LSP servers for structured code introspection. See README.md for architecture, supported languages, configuration, and tool documentation.
Build & Test
PyBuilder project. Python >= 3.11.
pyb # default task: analyze + publish
pyb run_unit_tests # unit tests only
pyb run_integration_tests # integration tests (requires clangd on PATH)
Dependencies: mcp (MCP Python SDK v2, MCPServer), lsprotocol, filelock, platformdirs
src/unittest/python/mcp_protocol_tests.py drives the server through a real MCP Client
(in-process and over a stdio subprocess) to cover protocol negotiation and tool listing.
It never calls a tool, so it never touches the daemon.
If karellen-lsp-mcp (and therefore mcp) is installed in the user site-packages
(pip install --user), run pyb from a dedicated virtualenv rather than the user-site pyb:
PyBuilder keeps user-site paths ahead of the build venv in the test subprocess, so tests
silently import the user-site mcp instead of the pinned one.
Project Layout
src/main/python/karellen_lsp_mcp/
server.py # MCP stdio frontend (entry point: main())
lsp_server.py # LSP proxy frontend (entry point: main()) — polyglot LSP proxy
daemon.py # Persistent daemon, owns LSP servers and project registry
daemon_client.py # Async client connecting frontends to daemon via Unix socket
lsp_client.py # Async wrapper around a single LSP server subprocess (JSON-RPC 2.0)
lsp_normalizer.py # Pluggable adapter for LSP server quirks (clangd readiness, retries)
lsp_adapter.py # LSP adapters: bridge detection → LSP server config (per-language)
detector.py # Project autodetection: build systems, IDE metadata, source roots
project_registry.py # Refcounted registry: project_id → LspClient
types.py # Dataclass response types for MCP tools
.claude-plugin/
plugin.json # Plugin manifest (name, version, description)
.mcp.json # MCP server configuration for the plugin
.lsp.json # LSP server configuration: maps file extensions to languages for Claude Code native LSP
hooks/
hooks.json # SessionStart (prerequisites), PostToolUse (compiler error detection)
scripts/
check-prerequisites.sh # Checks karellen-lsp-mcp, clangd, jdtls availability
detect-lsp-opportunity.sh # Detects compiler/build errors, suggests LSP tools
agents/
lsp-investigator.md # Autonomous agent for LSP-based code investigation
skills/
lsp-register/SKILL.md # Project registration skill
lsp-investigate/SKILL.md # Code investigation skill
docs/
c-cpp.md # C/C++ integration: detection, clangd, compile_commands.json
java-kotlin.md # Java/Kotlin integration: detection, jdtls, Gradle/Maven
python.md # Python integration: detection, pyright, virtual environments
rust.md # Rust integration: detection, rust-analyzer, Cargo workspaces
src/unittest/python/ # Unit tests (mocked, no external deps)
src/integrationtest/python/ # Integration tests (need clangd)
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.
- 16d ago Changed b80dc01828e6
- 27d ago Changed · +9 lines · +154 tokens per session 778a7e9d7f1f
- 1mo ago First seen · 123 lines · 1,637 tokens per session scan A e268ed48cd51
karellen-lsp-mcp CLAUDE.md is an instructions file published in the GitHub repository karellen/karellen-lsp-mcp (3 stars, last pushed 17d ago), licensed Apache-2.0. It adds 1,791 tokens to every session, about $0.0072 per session on Opus 5.5. 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 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.