lsp-setup

lsp-setup is a skill for Claude Code from DmitriyYukhanov/claude-plugins. It costs 111 tokens per session (1,693 once invoked), scanned B, original, MIT.

A setup and troubleshooting skill for the Language Server Protocol, a system that provides code navigation and diagnostics.

In plain words
What is it for?
Use it to set up, validate, or fix language-server support in a Claude Code project.
Why use it?
It helps configure code intelligence when features such as definition lookup, reference search, hover information, and diagnostics are unavailable.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the lsp-setup plugin — 1 skill shipped together

Good fit Use it to set up, validate, or fix language-server support in a Claude Code project.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add DmitriyYukhanov/claude-plugins
Claude Code
/plugin install lsp-setup

Made for: Claude Code.

Or install lsp-setup, the plugin that ships this one along with the rest of its 1 skill.

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 lsp-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/dmitriyyukhanov/claude-plugins/lsp-setup.svg)](https://agentmods.dev/skills/dmitriyyukhanov/claude-plugins/lsp-setup)
Your own site
<a href="https://agentmods.dev/skills/dmitriyyukhanov/claude-plugins/lsp-setup"><img src="https://agentmods.dev/badge/skills/dmitriyyukhanov/claude-plugins/lsp-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,693 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00111 $0.01693
Opus 5 $0.00056 $0.00847
Sonnet 5 $0.00022 $0.00339
Haiku 4.5 $0.00011 $0.00169

Measured 7d ago against content hash 0a4449856dc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

lsp-setup scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep "LSP servers loaded" ~/.claude/debug/latest
plugins/lsp-setup/skills/lsp-setup/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LSP Setup for Claude Code Projects

Set up Language Server Protocol support in Claude Code for the current project. This enables semantic code intelligence: go-to-definition, find-references, hover, document symbols, workspace symbols, diagnostics, and call hierarchy — all at ~50ms instead of 30-60s grep-based navigation.

State Detection

This skill operates as a state machine. On each invocation, detect the current state and resume from the appropriate step:

  1. No LSP configured → Start from Step 1 (detect languages)
  2. Binaries missing → Resume at Step 3 (install binaries)
  3. Plugins not installed → Resume at Step 4 (install plugins)
  4. Plugins installed but LSP returns "No LSP server available" → Step 5 (restart needed)
  5. LSP responds with symbols → Step 6 (validation complete, report success)

To detect state quickly: attempt an LSP documentSymbol call on any source file in the project. If it returns results, skip to validation. If "No LSP server available", check whether plugins are installed and binaries are on PATH.

Step 1: Detect Environment

Determine the current environment by checking uname -s:

  • MINGW* or MSYS* → MINGW (Git Bash on Windows)
  • /proc/version contains "microsoft" → WSL
  • Darwin → macOS
  • Otherwise → Linux

This affects install commands and PATH gotchas. Consult references/gotchas.md for environment-specific issues.

Step 2: Detect Languages

Scan the current project directory for language indicators using Glob. Check for source files (**/*.py, **/*.ts, **/*.cs, etc.) and project markers (**/pyproject.toml, **/tsconfig.json, **/Cargo.toml, etc.).

The complete detection pattern table is in references/lsp-registry.md under "Auto-Detection File Patterns" — use that as the authoritative source.

Present detected languages for confirmation. If a detected language has no official Claude Code LSP plugin, inform the user and ask whether to skip it.

Only the 12 languages in references/lsp-registry.md have official plugins. If auto-detection finds no supported languages, present the full list and let the user pick.

Read the full file on GitHub · 174 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 174 lines · 111 tokens per session scan B 0a4449856dc0

Subscribe to this mod's changes

lsp-setup is a skill published in the GitHub repository DmitriyYukhanov/claude-plugins (7 stars, last pushed 2d ago), licensed MIT. It adds 111 tokens to every session and 1,693 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

code-standards

Prabhdeep (Sonu) Singh's personal coding standards — the house rules and quality bar for how code gets written. INVOKE before writing, generating, refactoring, or reviewing ANY code in ANY language — schemas, endpoints, queries, logging, validation, error handling — even when nobody says "standards" or "style".…

PrabhdeepSingh/claude-plugins · 81 tokens

ticket-lifecycle

The ticket-as-control-plane rulebook — the single home for the tracker-operations contract, tracker resolution, the type/priority taxonomy, human-only trigger authorization, derived status, and trust boundaries. INVOKE when reading or writing tickets in a queue-driven flow, resolving a repo's tracker, or deciding…

PrabhdeepSingh/claude-plugins · 105 tokens

self-review

Surface the riskiest parts of the current diff so a reviewer knows where to look hardest — one inline pass on small diffs, parallel review lenses with adversarial synthesis on substantial ones. INVOKE PROACTIVELY whenever a change is finished and about to be handed off, reviewed, or shipped. It points attention …

PrabhdeepSingh/claude-plugins · 74 tokens

design-tree

Make design decisions as an explicit branching tree — genuine alternatives, decisive rationale, rejected branches preserved. INVOKE PROACTIVELY when planning or designing any implementation approach, or choosing between architectures, libraries, or data models — especially in plan mode. Skip trivial or forced changes…

PrabhdeepSingh/claude-plugins · 62 tokens

pr-conventions

Author PR descriptions from the right per-change-type template (the repo's own PULLREQUESTTEMPLATE wins), embed issue-tracker links, keep the description current as fixes land, and reply to human and bot review threads. INVOKE when opening or updating a PR or responding to reviewer comments — inside /sonu:ship or…

PrabhdeepSingh/claude-plugins · 80 tokens

tdd

Test-driven development — the red-green-refactor discipline for code that's correct by design, not by accident. INVOKE PROACTIVELY whenever writing or changing code, fixing a bug, adding or structuring tests, or choosing what to mock — even when nobody says "TDD" or "tests". (Tests are code held to…

PrabhdeepSingh/claude-plugins · 80 tokens