Opus Scout — Data & AI agent for Claude Code
Read-only Opus explorer for the Claude-only orchestration stack (fable-orchestration-claude-only).
How to install Opus Scout
Installs to ~/.claude/agents/remedegen-fable-orchestration-claude-only-opus-scout.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/RemeDegen/fable-orchestration-claude-only/HEAD/agents/opus-scout.md -o ~/.claude/agents/remedegen-fable-orchestration-claude-only-opus-scout.md Restart Claude Code, or start a new session, for it to be picked up.
What Opus Scout does
name: opus-scout description: Read-only Opus explorer for the Claude-only orchestration stack (fable-orchestration-claude-only). Maps code, traces flows, measures data with read-only queries, summarizes docs and compares options. Returns understanding — a compact report — never a diff. Use for every context-gathering delegation before a builder is spawned. tools: Read, Glob, Grep, Bash, WebFetch, WebSearch model: opus effort: high maxTurns: 40
Opus Scout
You gather context for an orch
Alternatives in Data & AI
- Vision — GSD-2 is the orchestration layer between you and AI coding agents 5.7k ★
- Info Disclosure — Information Disclosure specialist (H1 #18, CWE-200/209/215/538/668/798) 812 ★
- Harness Scout — Picks the right AI agent harness for a described task or project 801 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Advanced Risk
Use this agent proactively for advanced risk modeling, quantitative risk measures, options analytics, and soph
Read Only Explorer
Maps how code actually works — call paths, call sites, data flow, existing patterns, ownership boundaries, and
Fullstack API Specialist
API data scout for fullstack development. Use to explore backend APIs, parse OpenAPI schemas, detect auth meth
Claude Advisor
Second-opinion advisor running Claude's most capable model (Fable 5). Consult at commitment boundaries — befor
Amoa Task Summarizer
Summarizes verbose task outputs into minimal reports for orchestrator consumption. Requires AI Maestro install
UI Behavior Reviewer
Compares prototype vs live UI behavior - state mismatches from the capture fingerprints, copy, labels, compone
Related Skills
Design Scout
Research-first UI/UX design for AI coding agents (Claude Code, Codex, Cursor): reads expert sources with verif
Agent Explorer
Work as the Explorer agent — Maps an unfamiliar workspace and finds the exact code, files, and execution paths
Pbi Dax
Delegate measure work or a read-only DAX question to pbi-dax: create/optimize measures with validation and sam