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/boostvolt/claude-code-lsps/claude-mdgit clone --depth 1 https://github.com/boostvolt/claude-code-lspsWhat 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 | $0.00541 | $0.00541 |
| Opus 5 | $0.00270 | $0.00270 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
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.
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 executeextensionToLanguage: 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:
- Check if LSP binary exists → exit silently if yes
- Check if language runtime exists → show install instructions if no
- Attempt auto-install → show PATH instructions if needed
Adding a New Plugin
- Create a new directory with the plugin name
- Add
.claude-plugin/plugin.jsonwith name, description, version, and author - Add
.lsp.jsonwith command and extensionToLanguage mapping - Add
hooks/hooks.jsonto run auto-install on SessionStart - Add
hooks/check-<name>.shauto-install script - 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" } }
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 · 61 lines · 541 tokens per session scan A 3ac298fc388d
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.
Other instructions, from other repositories
Amarok-Hider AGENTS.md
Instructions for deltazefiro/Amarok-Hider, covering amarok, project overview, build, e2e test and agent rules.
AppClaw CLAUDE.md
Instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
MobiAI-Core CLAUDE.md
Instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.
ConsultMe CLAUDE.md
Instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.