code-analysis
Codebase investigation and semantic search. Maps architecture, traces callers and callees, and ranks symbols by PageRank through the mnemex AST engine, with a read-only detective agent for deep dives.
| Version | 5.4.1 |
| Marketplace | magus |
| Commands | 3 |
| Subagents | 1 |
| Skills | 4 |
| MCP server | no |
| Hooks | yes |
Install
claudeup
Find code-analysis on the Plugins tab and turn it on. claudeup registers the magus
marketplace if you do not have it, and installs what the plugin needs to actually run —
binaries, MCP servers, CLI tools.
For a team, press s to save your plugins as a profile and commit it. Everyone else runs
claudeup install — see Teams and profiles.
Prefer to do it by hand? Installing Magus has the manual path.
How to run these: understanding a codebase — what to type, what it asks you, and which options change the outcome.
When to reach for it
- Use when orchestrating multi-agent code analysis —
mnemex-orchestration - Use this agent when you need to investigate, analyze, or understand patterns in a codebase —
detective
Commands
| Command | What it does |
|---|---|
/code-analysis:analyze | Deep codebase investigation to understand architecture, trace functionality, find implementations, and analyze code patterns |
/code-analysis:code-analysis-help | Show comprehensive help for the Code Analysis Plugin - lists agents, commands, skills, and usage examples |
/code-analysis:setup | Add mnemex MCP tools documentation to project CLAUDE.md and verify setup |
Subagents
Dispatched with the Agent tool, each in its own context window.
| Agent | What it does |
|---|---|
code-analysis:detective | Use this agent when you need to investigate, analyze, or understand patterns in a codebase. |
Skills
| Skill | What it covers |
|---|---|
code-analysis:deep-analysis | Runs a multi-perspective codebase audit using all mnemex AST commands with PageRank and chain-of-thought reasoning. |
code-analysis:investigate | Routes code investigation to the right mnemex AST workflow — architecture (map/PageRank), implementation (callers/callees), tests, or debugging. |
code-analysis:mnemex-orchestration | Runs mnemex once and shares its output across parallel agents, with role-based command mapping and session lifecycle handling. Use when orchestrating multi-agent code analysis. |
code-analysis:mnemex-search | Performs semantic code search and AST analysis via mnemex MCP/CLI — map, symbol, callers, callees, context, PageRank. |
Hooks
This plugin installs hooks. They run automatically and are the usual first place to look if its behaviour stops firing.
Source
plugins/code-analysis/ on GitHub, including its full README.