Stroi Explorer — Development agent for Claude Code
Use this agent when a planner or skill needs ground truth about the codebase before designing against it.
How to install Stroi Explorer
Installs to ~/.claude/agents/stroi-stroi-stroi-explorer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Stroi/stroi/HEAD/agents/stroi-explorer.md -o ~/.claude/agents/stroi-stroi-stroi-explorer.md Restart Claude Code, or start a new session, for it to be picked up.
What Stroi Explorer does
name: stroi-explorer description: Use this agent when a planner or skill needs ground truth about the codebase before designing against it. Typical triggers include mapping the patterns and conventions of a scope, locating the integration points a new feature must touch, and fanning out several read-only surveys in parallel. Read-only cartographer — never invoke it to write code. tools: Read, Grep, Glob model: sonnet color: cyan effort: medium
You are **stroi-explorer**, a read-only rec
Alternatives in Development
- Review Agent — You are a specialized review agent 3.6k ★
- Eval Engineer — GAIA evaluation framework specialist 1.5k ★
- Tech Stack Researcher — Use this agent when the user is planning new features or functionality and needs guidance on technology choice 1.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Stroi Planner
Use this agent when a goal needs expanding into a concrete, file-level plan before any code is written. Typica
Stroi Developer
Use this agent when an approved stroi plan needs its code actually written. Typical triggers include building
Wiki Adapter PRD
Use this agent when mapping foreign PRD formats into vault pages during automated processing cycles. Typical t
Proj Work
Use this agent when creating or executing work items during automated development cycles. Typical triggers inc
Exploit Agent
Use this agent when a recon findings file already exists for a target and an initial-access foothold needs ide
Privesc Agent
Use this agent when there's an initial low-privilege shell on an authorized lab target and privilege escalatio
Related Skills
Rails AI Context
45 MCP tools that give AI coding agents ground truth about your Rails app: schema, models, routes, controllers
Closeout
Post-project audit. Diffs SCOPE.md deliverables against ground truth using tier-aware verification (code-done
Claude Boot Stats
Per-component token cost analyzer for Claude Code first-turn context: HTTP intercept proxy + Qwen3 BPE + groun
