Read Only Explorer — Data & AI agent for Claude Code
Maps how code actually works — call paths, call sites, data flow, existing patterns, ownership boundaries, and the smallest safe insertion point for a change.
How to install Read Only Explorer
Installs to ~/.claude/agents/arcanedge-ai-coding-agent-playbook-claude-code-read-only-explorer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ArcanEdge-AI/coding-agent-playbook-claude-code/HEAD/agents/read-only-explorer.md -o ~/.claude/agents/arcanedge-ai-coding-agent-playbook-claude-code-read-only-explorer.md Restart Claude Code, or start a new session, for it to be picked up.
What Read Only Explorer does
name: read-only-explorer description: Maps how code actually works — call paths, call sites, data flow, existing patterns, ownership boundaries, and the smallest safe insertion point for a change. Use when you need grounded answers about an unfamiliar area before designing or editing, or when you need every place a symbol, route, event, config key, or schema field is used. Not for trivial single-file lookups you can do faster yourself, and not for making changes. model: haiku permissionMode:
Alternatives in Data & AI
- Supabase Inference Explorer — Use proactively for exploring creative, non-obvious applications of Supabase Edge Functions, AI (embeddings an 64 ★
- Checkpoint Planner — Breaks a large feature into small, ordered, gated checkpoints and writes them as JSON to .ai-engineering/workf 61 ★
- App Explorer — Use this agent for autonomous AI-powered exploration of web applications to discover features, flows, and func 37 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Explorer Critic
Dataset assessor for the data-finder skill. Applies a 5-point critique to each dataset proposed by the Explore
Prompt Reviewer Code
Locates LLM call sites in any codebase (Go, Python, TypeScript, anything), reconstructs the resolved prompt fr
Reviewer Correctness
Correctness specialist reviewer. Verifies code actually works as intended: intent-implementation alignment, in
Sf Org Verifier
Verifies a Salesforce change in the live org after deployment - smoke probes, data and limit queries, log capt
Admin Portal Architect
Use when auditing the admin console/back-office: which pages actually work, silent empty results, dead routes,
Maps Miner
Works Google Maps-type data for the target region — rating and review-count profiles, review-language mix, nei
Related Skills
Agent Explorer
Work as the Explorer agent — Maps an unfamiliar workspace and finds the exact code, files, and execution paths
Twin Sparrow Grounded Collaboration
Multi-agent collaboration discipline: claims must carry evidence, requests must be read for their object befor
Al Architecture Md
Write or refresh ARCHITECTURE.md using an 8-question structure that captures intent, boundaries, ownership, an