analyze-code

A command guide for using language-server tools to analyse code by understanding types, symbols, references, dependencies, and diagnostics.

In plain words
What is it for?
Checking project-wide errors and warnings, tracing symbol references, examining dependencies, and investigating code with the appropriate language-server features.
Why use it?
It helps find errors and relationships across files more accurately than searching for text alone.

Command for Claude Code

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 commands/mizchi/lsmcp/analyze-code
Clone the repo
git clone --depth 1 https://github.com/mizchi/lsmcp

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,682 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 $0.00000 $0.01682
Opus 5 $0.00000 $0.00841
Sonnet 5 $0.00000 $0.00336
Haiku 4.5 $0.00000 $0.00168

Measured 2d ago against content hash 3cbf31f4e25a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-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 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/commands/analyze-code.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Analysis with LSMCP MCP

This command uses the LSMCP (Language Server MCP) tools to perform rapid semantic code analysis, leveraging language server capabilities for more accurate results than traditional grep/search approaches.

Overview

LSMCP provides semantic code analysis through language server protocol, enabling:

  • Type-aware error detection
  • Symbol reference tracking
  • Cross-file dependency analysis
  • Real-time diagnostics

Command Template

# Rapid Code Analysis Task

Project Root: <PROJECT_PATH>
Target Language: <LANGUAGE>
Analysis Goal: <SPECIFIC_GOAL>

Execute the following analysis phases:

## Phase 1: Capability Check (5 seconds)
Verify available LSP features:

mcp__lsmcp-__check_capabilities


## Phase 2: Project-wide Diagnostics (10 seconds)
Collect all errors and warnings:

mcp__lsmcp-__get_all_diagnostics

  • root: "<PROJECT_PATH>"
  • pattern: "**/*.<FILE_EXTENSION>"
  • severityFilter: "error" # Start with errors only
  • useGitignore: true

If few errors found, repeat with severityFilter: "warning"

## Phase 3: Symbol Analysis (5 seconds per symbol)
For critical functions/classes:

mcp__lsmcp-__find_references

  • root: "<PROJECT_PATH>"
  • filePath: "<RELATIVE_FILE_PATH>"
  • line: <LINE_NUMBER>
  • symbolName: "<SYMBOL_NAME>"

## Phase 4: Type Verification (3 seconds per location)
For suspicious code locations:

mcp__lsmcp-__get_hover

  • root: "<PROJECT_PATH>"
  • filePath: "<RELATIVE_FILE_PATH>"
  • line: <LINE_NUMBER>
  • target: "<CODE_SNIPPET>"

## Phase 5: Unused Code Detection
Identify symbols with zero references:

mcp__lsmcp-__find_references

  • Check exported functions/classes
  • Flag items with 0 references

## Report Format
1. Executive Summary
   - Total errors/warnings count
   - Critical issues requiring immediate attention
   
2. Detailed Findings
   - Group by severity (Error > Warning > Info)
   - Include file:line references
   - Show affected symbol names
   
3. Impact Analysis
   - Number of files affected
   - Cross-module dependencies
   
4. Recommendations
   - Priority fixes
   - Refactoring suggestions
   - Code quality improvements

Read the full file on GitHub · 232 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 · 232 lines · 0 tokens per session scan A 3cbf31f4e25a

Subscribe to this mod's changes

analyze-code is a command published in the GitHub repository mizchi/lsmcp (453 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,682 tokens. 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.