lsp-dead-code

lsp-dead-code is a skill for Claude Code, Codex from blackwell-systems/agent-lsp. It costs 43 tokens per session (2,172 once invoked), scanned A, original, MIT.

A code-audit check that finds exported functions, classes, types, or other public symbols with no references elsewhere in the workspace. Exported symbols are code elements made available for use by other files or packages.

In plain words
What is it for?
Use it to inspect a file for unused exports, identify legacy public code, and assess which API elements may be removable after manual verification.
Why use it?
It helps surface possible dead code and unused public API before cleanup or release. The results are candidates for review, not proof that deletion is safe.

Skill for Claude CodeCodex

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 skills/blackwell-systems/agent-lsp/lsp-dead-code
Any agent
npx skills add blackwell-systems/agent-lsp --skill lsp-dead-code
Clone the repo
git clone --depth 1 https://github.com/blackwell-systems/agent-lsp

Made for: Claude Code, Codex.

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-dead-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/blackwell-systems/agent-lsp/lsp-dead-code.svg)](https://agentmods.dev/skills/blackwell-systems/agent-lsp/lsp-dead-code)
Your own site
<a href="https://agentmods.dev/skills/blackwell-systems/agent-lsp/lsp-dead-code"><img src="https://agentmods.dev/badge/skills/blackwell-systems/agent-lsp/lsp-dead-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,172 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00043 $0.02172
Opus 5 $0.00022 $0.01086
Sonnet 5 $0.00009 $0.00434
Haiku 4.5 $0.00004 $0.00217

Measured 5d ago against content hash 60e24a2da4d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

lsp-dead-code 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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/lsp-dead-code/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requires the agent-lsp MCP server.

lsp-dead-code

Audit an exported symbol list for zero-reference candidates. Calls list_symbols to enumerate symbols, then checks each exported symbol with find_references to find callers. Produces a classified report.

When to Use

Use this skill when you want to identify dead code in a file — exported symbols that are defined but never called anywhere in the workspace. Common use cases:

  • Cleaning up APIs before a release
  • Identifying legacy exports that can be safely removed
  • Auditing a package for unused public surface area

Important: This skill surfaces candidates. Always review results manually before deleting anything. See the Caveats section below.

What counts as "exported"

Language Exported means...
Go Identifier starts with an uppercase letter (e.g. MyFunc, MyType)
TypeScript Has export keyword; or is a public class member (no private)
Python Not prefixed with _; or explicitly listed in __all__
Java/C# Has public or protected visibility modifier
Rust Has pub keyword

Prerequisites

If LSP is not yet initialized, call mcp__lsp__start_lsp with the workspace root first:

mcp__lsp__start_lsp({ "root_dir": "/your/workspace" })

agent-lsp supports auto-inference from file paths, so explicit start is only required when switching workspaces or on a cold session.

Step 0 — Verify indexing is complete (mandatory)

Do not skip this step. An under-indexed workspace returns [] for symbols that ARE referenced, producing false dead-code candidates.

Pick one symbol you know is actively used (e.g. the primary constructor, a widely-called utility function). Call find_references on it:

Read the full file on GitHub · 237 lines

Files

What ships with it

1 file 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. 5d ago First seen · 237 lines · 43 tokens per session scan A 60e24a2da4d8

Subscribe to this mod's changes

lsp-dead-code is a skill published in the GitHub repository blackwell-systems/agent-lsp (121 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 2,172 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

authoring-schemas

Author a mache projection schema (Topology→Node→Leaf) that maps structured data or source code into a filesystem/graph. Use when creating or debugging a -schema.json for a new data source (SQLite/JSON) or a new source language. Covers both dialects — tree-sitter S-expression selectors for code, and JSONPath selectors…

agentic-research/mache · 111 tokens

authoring-smell-rules

Add a findsmells rule to mache — a SQL query over the projected code graph that surfaces a code smell (duplication, complexity, dead code, drift). Use when adding or debugging a SmellRule in cmd/smellrules.go or an external $MACHESMELLRULESDIR rule. Covers the SmellRule struct, the standalone-vs-ast table capability…

agentic-research/mache · 102 tokens

mache-explore

Mount a mache FUSE filesystem inside the project directory so agents can explore structured data without per-file permission prompts.

agentic-research/mache · 27 tokens

analyze-usage

Use when asked to analyze codescout tool usage, check for error patterns, audit tool health, generate a usage report, spot anti-patterns, or clear usage statistics to start fresh.

mareurs/codescout · 42 tokens

code-intelligence

Universal, safe, and professional code modification and refactoring environment for 50+ languages. Use when editing source files to prevent syntax breakage, perform project-wide type-aware renames (LSP), or distill large command output to save context window tokens.

naranor/code-intelligence-skill · 58 tokens

claude

Skill "claude" from paladini/locus-mcp, covering claude code skill (stub), when to use locus, when to use grep, mcp registration and status.

paladini/locus-mcp · 0 tokens