Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when spawning subagents via the Agent or Workfl
mdr add oaustegard/claude-skills/agent-routing@v2.1.0mdr add oaustegard/claude-skills/agent-routing@sha256:c79a17c2dfa3a0d2[](https://markdownregistry.com/a/art_strtmpfeu5mja4fj)
0 badge views in 30 days
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.1.0 latest | 2026-09-04 | aa42cd7 | 19,425 B | A | view · diff |
| v2.0.0 | 2026-08-18 | 705addc | 15,658 B | A | view · diff |
| v1.4.0 | 2026-08-16 | 27da81d | 13,097 B | A | view · diff |
| v1.3.0 | 2026-07-24 | 4118be3 | 11,798 B | A | view · diff |
| v1.2.0 | 2026-07-16 | 1ccd62f | 7,232 B | A | view |
oaustegard/claude-skills · 147 stars · license MIT · pushed 2026-09-05 · branch main
GET https://markdownregistry.com/api/v1/artifacts/art_strtmpfeu5mja4fj GET https://markdownregistry.com/api/v1/resolve?ref=oaustegard/claude-skills/agent-routing GET https://markdownregistry.com/api/v1/blob/c79a17c2dfa3a0d2d242563bff0e061ca997e2ef567a1700f652c4b69434447c