agent-router

Plugin agent-router in EONRaider/agent-router. Commands read from the repo's manifest — 1 month ago.

Skills (3)

• init

  Opt the current project in to agent-router by creating its overlay file (.claude/agent-router.json) and enabling the committed spawn log. Use when the user runs /agent-router:init, asks to set up or enable agent-router in a project, or when the session start message says the project has not opted in

• report

  Show the agent-router report for the current project (spawns, problems and estimated spend per tier) and walk the user through its proposals, accepting or rejecting each one. Use when the user runs /agent-router:report, asks how the routing tiers are performing, asks whether a tier should be resized

• routing

  Choose the right agent-router tier (scout, worker, analyst or judge) before spawning a subagent with the Agent tool. Use whenever you are about to delegate work to a subagent, when a spawn was rejected by the agent-router hook, or when deciding whether a task can go to a cheaper agent. Covers how to

Subagents (4)

• analyst

  Research and synthesis tier (Sonnet, high effort). Use for investigating a question across many files or sources, comparing options, tracing how a system behaves, or planning an approach, where the result is a reasoned account and not a single checkable fact. Not for the final review or sign-off of

• judge

  Judgment tier (Opus, high effort, no file edits). Use for code review, adversarial critique, security or design calls, verifying another agent's work, and any task where a wrong answer is costly and hard to detect. Judgment work always comes here; it is never sent to a cheaper tier.

• scout

  Cheapest tier (Haiku, low effort, read-only). Use for lookups, finding files or symbols, status reads, and bounded extraction where the answer is a fact you can check at a glance. Not for implementation, synthesis across sources, review, audit or any judgment call.

• worker

  Default implementation tier (Sonnet, medium effort). Use for work with a checkable result: writing or changing code against tests, a diff with a clear acceptance check, mechanical refactors, running a defined procedure. Not for review, audit or design decisions, and not for open-ended research.

Hooks (5)

• SessionStart

  python3

• PreToolUse

  python3

• PostToolUse

  python3

• PostToolUseFailure

  python3

• SubagentStop

  python3

Similar plugins