Load the dev-workflows task-complexity classification rules and model fallback chain. Invoked at the classification step by the 14 pipeline commands (`/implement`, `/document`, `/epics`, `/release-notes`, `/vuln`, `/upgrade`, `/docs-profile`, `/idea`, `/create-prd`, `/update-prd`, `/create-ard`, `/specify`, `/design`, `/ready`), because slash-command bodies cannot expand ${CLAUDE_PLUGIN_ROOT} themselves.
Scanned 8/31/2026
Install to Claude Code
Skills Directorynpx -y skills add ihudak/ihudak-claude-plugins --skill model-routing --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Model Routing?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ihudak-model-routing)More formats (shields.io, HTML) on the badges page.
---
name: model-routing
description: Load the dev-workflows task-complexity classification rules and model fallback chain. Invoked at the classification step by the 14 pipeline commands (`/implement`, `/document`, `/epics`, `/release-notes`, `/vuln`, `/upgrade`, `/docs-profile`, `/idea`, `/create-prd`, `/update-prd`, `/create-ard`, `/specify`, `/design`, `/ready`), because slash-command bodies cannot expand ${CLAUDE_PLUGIN_ROOT} themselves.
user-invocable: false
allowed-tools: Read
---
# Model routing
Read the authoritative classification rules and model fallback chain:
`${CLAUDE_PLUGIN_ROOT}/references/model-routing/classification.md`
Then classify the current task as exactly one of `SIMPLE`, `MODERATE`,
`SIGNIFICANT`, or `HIGH-RISK` using the criteria in that file, and apply the
model fallback chain and `model_routing` handoff block it defines. That file is
the single source of truth — do not paraphrase or cache its contents here.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
