model-routing
Model selection strategy for subagents — haiku for exploration, sonnet for implementation, opus for architecture/security
npx skills add majiayu000/claude-skill-registry --skill model-routing-itsmattg-property-tracker --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Model Routing Strategy Route subagents to the cheapest sufficient model. The `model` parameter on Task tool calls controls this. ## When to Run - Before dispatching Task subagents (which model to use?) - When a subagent fails quality review (escalate to next tier?) - When reviewing Ralph epic configuration ## Routing Table | Task Type | Model | Rationale | |-----------|-------|-----------| | Exploration/search (Explore agents) | haiku | Fast, cheap, sufficient for find/read | | Simple edits, single-file changes | haiku | Clear instructions, low complexity | | Documentation writing | haiku | Structure is straightforward | | Multi-file implementation | sonnet | Best balance for coding tasks | | PR/code review | sonnet | Understands context, catches nuance | | Test writing | sonnet | Needs pattern matching, not deep reasoning | | Complex architecture, planning | opus | Deep reasoning required | | Security analysis | opus | Can't afford to miss vulnerabilities | | Debugging complex bugs | opus | Needs to hold entire system in mind | | Ralph subagent tasks | sonnet | Default for autonomous execution, escalate on failure | ## Fallback Escalation When a subagent fails quality review, re
- When to Run
- Routing Table
- Fallback Escalation
- Examples
- Cost Reference
What does the model-routing skill do?
Model selection strategy for subagents — haiku for exploration, sonnet for implementation, opus for architecture/security
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill model-routing-itsmattg-property-tracker --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.