setup_routinglisted

Configures per-project model and effort routing so Opus + high/xhigh thinking is spent only where it changes output quality and high-volume mechanical work runs on Sonnet. Use when the user says "setup_routing", "/setup_routing", "set up model routing", "configure model routing", "route tasks by model", or "make this project use Opus/Sonnet per task". Independently analyzes the repo, classifies it into a sensitivity profile (Opus-dominant, Mixed core/scaffold, Sonnet-default, or a Balanced fallback), proposes a tag-driven routing policy, waits for explicit confirmation, then writes a sentinel-delimited routing block into the project CLAUDE.md. The pinned-model executor subagents the policy references ship with the plugin (agents/); customized per-project copies in .claude/agents/ are an opt-in override.
blendsdk/claude-codeops · ★ 4 · AI & Automation · score 75

Install: claude install-skill blendsdk/claude-codeops

# Model & Effort Routing Setup (`setup_routing`) > **CodeOps Skills Version**: 3.20.0 Configure **per-project model and effort routing** for the project the user is currently in, so that expensive reasoning (Opus, high/xhigh thinking) is spent only where it changes output quality, and high-volume mechanical work runs on Sonnet. Invoked as `/codeops:setup_routing` or the typeable alias `/setup_routing`. ## The two-layer principle (preserve this throughout) Routing has **two layers**, and they must stay coordinated: 1. **Policy layer (soft, behavioral).** A block in the project's `CLAUDE.md` decides *which model* each phase runs on — inline-first — and which pinned executor backs a dispatch when one is warranted, expressed as a rule over task tags. 2. **Enforcement layer (hard, guaranteed).** Each executor subagent's frontmatter pins both `model:` (which model runs) and `effort:` (which reasoning effort runs) when that executor is invoked. Claude Code enforces both, overriding the user's session/`settings.json`/env config — so routing works *regardless of what the user has already configured*. The sole exception is the `CLAUDE_CODE_SUBAGENT_MODEL` env var, which sits above subagent frontmatter and forces every subagent onto one model (a deliberate global cost-cap escape hatch — surface it in Phase 5). > The policy is only trustworthy because the pinned executors exist to back it. Since v3.2.0 the > two executors (`plan-task-executor`, `plan-task-execu