claude-code-lsps CLAUDE.md

Repository instructions for a collection of language-server plugins for Claude Code. A language server adds code understanding such as definitions, references, hover information, and diagnostics.

In plain words
What is it for?
Adding or maintaining language plugins, configuring file-extension mappings, defining the language-server command, and writing startup checks for missing runtimes or binaries.
Why use it?
They define the standard plugin files and explain how each plugin connects a programming language to Claude Code and installs its required language tool.

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/boostvolt/claude-code-lsps/claude-md
Clone the repo
git clone --depth 1 https://github.com/boostvolt/claude-code-lsps
Per session 541 This file is loaded in full into every session.
When invoked 541 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 $0.00541 $0.00541
Opus 5 $0.00270 $0.00270
Sonnet 5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured 2d ago against content hash 3ac298fc388d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-lsps 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 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

This is a collection of LSP (Language Server Protocol) plugins for Claude Code. Each plugin enables language intelligence features (go-to-definition, find-references, hover, diagnostics) for a specific programming language.

Repository Structure

Each plugin is a self-contained directory with this structure:

<plugin-name>/
├── .claude-plugin/
│   └── plugin.json      # Plugin metadata
├── .lsp.json            # LSP server configuration (auto-discovered)
└── hooks/
    ├── hooks.json       # Hook definitions (auto-discovered, runs on SessionStart)
    └── check-<name>.sh  # Auto-install script for the LSP binary

Key Files

.lsp.json

Configures the language server. Only required fields:

  • command: The LSP binary to execute
  • extensionToLanguage: Maps file extensions to language IDs

Optional: args, loggingConfig (for debug logging support)

hooks/check-*.sh

Auto-install scripts that run on session start. Pattern:

  1. Check if LSP binary exists → exit silently if yes
  2. Check if language runtime exists → show install instructions if no
  3. Attempt auto-install → show PATH instructions if needed

Adding a New Plugin

  1. Create a new directory with the plugin name
  2. Add .claude-plugin/plugin.json with name, description, version, and author
  3. Add .lsp.json with command and extensionToLanguage mapping
  4. Add hooks/hooks.json to run auto-install on SessionStart
  5. Add hooks/check-<name>.sh auto-install script
  6. Update README.md: add to Available Plugins table and Manual Installation section

Note: .lsp.json and hooks/hooks.json are auto-discovered from default locations - no need to reference them in plugin.json.

Debug Logging

Plugins that support args/env-based logging should include loggingConfig:

  • Args-based: "loggingConfig": { "args": ["--verbose"] }
  • Env-based: "loggingConfig": { "env": { "DEBUG": "true" } }

Read the full file on GitHub · 61 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 · 61 lines · 541 tokens per session scan A 3ac298fc388d

Subscribe to this mod's changes

claude-code-lsps CLAUDE.md is an instructions file published in the GitHub repository boostvolt/claude-code-lsps (178 stars, last pushed 3mo ago), licensed MIT. It adds 541 tokens to every session, about $0.0027 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.