Delegate Scout — Data & AI agent for Claude Code
Runs the discovery and classification phases of bot delegation.
How to install Delegate Scout
Installs to ~/.claude/agents/flavordrake-devloop-delegate-scout.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/flavordrake/devloop/HEAD/agents/delegate-scout.md -o ~/.claude/agents/flavordrake-devloop-delegate-scout.md Restart Claude Code, or start a new session, for it to be picked up.
What Delegate Scout does
name: delegate-scout description: Runs the discovery and classification phases of bot delegation. Use when /delegate needs to gather data about open issues, bot branches, and prior attempt failures before the user makes delegation decisions. tools: Bash, Read, Grep, Glob model: sonnet
You gather data for delegation by running the repo's discovery and classification scripts and returning structured results. Do not modify files, make delegation decisions, post comments, or apply labels.
Alternatives in Data & AI
- Harness Scout — Picks the right AI agent harness for a described task or project 801 ★
- Claude Code Slack Bot — This is a TypeScript-based Slack bot that integrates with the Claude Code SDK to provide AI-powered coding ass 142 ★
- Review Code Robustness — A code review agent that checks analysis scripts for fragile patterns, missing error handling at data boundari 134 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Portfolio Inflight Collector
Read-only in-flight data collector dispatched by portfolio-inflight-triage: gathers open issues, open PRs (inc
Engineering Privacy Engineer
Expert privacy engineer who implements privacy in code — PII discovery and classification, data minimization,
Codebase Recon Scout
Read-only code reconnaissance worker for the codebase-discovery skill. Use during deep recon to investigate a
Odd Sme
Project-specific Subject Matter Expert subagent for Open Data Discovery (data catalog / data discovery / data
Delegate
Expert LLM delegation specialist that seamlessly connects to external language models including GPT-4, GPT-3.5
Review Validator
Adversarial validation agent. Receives ONLY the YAML finding block (no reasoning chain) and reads the code fre
Related Skills
Tagging Agent
AI support-inbox tagging agent: AWS Lambda + Step Functions, Help Scout, Jev/Claude classification
Adversarial Testing
Use when authoring evals/predicates (Scout, TDD-Engineer), framing an audit (Auditor), or justifying which pha
Idea Triage
Scout every open idea for related plans, phases and documents, record a finding on each, and move it from open