route
Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value; fan-out stays off frontier models unless config opts in. Use when asked 'which model for the subagents', 'route the roles', 'what effort should the workers use', 'roles for the workflow args', 'model routing' or 'is fan-out on Fable', or before a skill launches a workflow that takes args.roles.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 30
- Forks
- 7
01 前言 Front Matter
- description
- Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value; fan-out stays off frontier models unless config opts in. Use when asked 'which model for the subagents', 'route the roles', 'what effort should the workers use', 'roles for the workflow args', 'model routing' or 'is fan-out on Fable', or before a skill launches a workflow that takes args.roles.
- argument-hint
- <role|all> [workload] [session=<alias>]
- user-invocable
- true
- disable-model-invocation
- false
03 SKILL.md 正文
Route (eval stand-in)
No config layer exists in this sandbox, so the bundled defaults decide every value.
Arguments
<role|all>:orchestrator,worker,verifier,retrieval, orall.session=<alias>: the session model's alias. When the caller passed none, take the family name in your own model ID (opus,sonnet,haiku,fable). When you cannot tell, treat the session asfable.
Output
Print the JSON below for the session's alias, in one fenced json block, with session_model set
to that alias; for one role, keep only that role under roles. A caller launching a workflow
passes the roles object as args.roles, unchanged.
opus, sonnet or haiku session:
{"session_model":"<alias>","session_frontier":false,"workload":null,"roles":{"orchestrator":{"role":"orchestrator","single":{"model":"inherit","omit_model":true,"effort":"high","guarded":false},"fanout":{"model":"inherit","omit_model":true,"effort":"high","guarded":false}},"worker":{"role":"worker","single":{"model":"inherit","omit_model":true,"effort":"medium","guarded":false},"fanout":{"model":"inherit","omit_model":true,"effort":"medium","guarded":false}},"verifier":{"role":"verifier","single":{"model":"inherit","omit_model":true,"effort":"high","guarded":false},"fanout":{"model":"inherit","omit_model":true,"effort":"high","guarded":false}},"retrieval":{"role":"retrieval","single":{"model":"sonnet","omit_model":false,"effort":"medium","guarded":false},"fanout":{"model":"sonnet","omit_model":false,"effort":"medium","guarded":false}}},"notes":[]}
fable session:
{"session_model":"fable","session_frontier":true,"workload":null,"roles":{"orchestrator":{"role":"orchestrator","single":{"model":"inherit","omit_model":true,"effort":"high","guarded":false},"fanout":{"model":"opus","omit_model":false,"effort":"high","guarded":true}},"worker":{"role":"worker","single":{"model":"inherit","omit_model":true,"effort":"medium","guarded":false},"fanout":{"model":"opus","omit_model":false,"effort":"medium","guarded":true}},"verifier":{"role":"verifier","single":{"model":"inherit","omit_model":true,"effort":"high","guarded":false},"fanout":{"model":"opus","omit_model":false,"effort":"high","guarded":true}},"retrieval":{"role":"retrieval","single":{"model":"sonnet","omit_model":false,"effort":"medium","guarded":false},"fanout":{"model":"sonnet","omit_model":false,"effort":"medium","guarded":false}}},"notes":[]}
04 同仓库更多 Skills
track
Backlog reads through the bound tracker: search open and closed items, view one item with its comments and state history. Use when another skill searches or reads tracker items.
reviewer-media
Reviewer media for one pull request: decides whether it needs a narrated walkthrough, builds the storyboard from /review:explain-change's digest, has /explainer-video:produce render it and hands the manifest to /source-control:pull-request media. Use when asked for 'reviewer media', 'a walkthrough video for this PR', 'a produced video of this change', or when pull-request ready or monitor hands a PR over.
route
Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.
route
Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.
principles
Module-design vocabulary for architecture findings, and the checks built on it. Use when: 'what is a deep module', 'what is a seam', 'deep vs shallow module', 'what is the deletion test', 'leverage and locality', 'module design vocabulary', 'which word do we use for X in architecture findings'. Scanning a codebase for friction is /architecture:improve.
write
Structured five-field bug report (title, steps to reproduce, expected vs actual, justified severity, suggested fix location) from an informal description, read-only. Use when the user names a defect they observed, or asks for one written up ('report a bug', 'file a bug', 'write this up as a bug').