eval-agents

# Agent Evaluator Discover all agents in scope, score each one across five criteria, then run an interactive session to confirm or improve them one by one. Agents are not just scripts: they are callable units selected by orchestrators based on their description. A vague description silently breaks multi-agent workflows. The goal here is not just scoring; it is leaving every agent correctly scoped, correctly modeled, and safe to call from an orchestrator. ## When to Use - First time auditing an agent fleet before wiring it into an orchestration pipeline - An orchestrator keeps selecting the wrong agent for a task - After copying agents from another project or importing a plugin - A new agent was added; checking whether it conflicts with existing ones - Periodic hygiene: "do all these agents still do something distinct?" ## Key Concepts ### Agent file locations | Location | Scope | Committed? | |---|---|---| | `.claude/agents/<name>.md` | Project (flat file) | Yes | | `.claude/agents/<name>/AGENT.md` | Project (directory-based) | Yes | | `~/.claude/agents/<name>.md` | User-level | No | | Plugin `agents/*.md` | Per plugin | Yes (in plugin) | Both flat files and directory-based agents are valid. The `name:` field is the identifier used by orchestrators and hooks (passed as `agent_type`). The filename does not have to match, though keeping them aligned is recommended. ### Frontmatter fields | Field | Required | Notes | |---|---|---| | `name` | Yes | Unique identifier (ke...