cbbkrd-tech/jl-finishes / .claude/skills/claude-routing
claude-routing
VerifiedSkills for the Claude Code model routing system — managing persistent subagents (haiku/sonnet/opus).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.1 KB |
SKILL.md
View on GitHub---
name: claude-routing
description: Skills for the Claude Code model routing system — managing persistent subagents (haiku/sonnet/opus).
---
# Claude Routing Skills
## /route
Explicitly evaluate and route a task to the appropriate subagent.
**Usage:** `/route <task description>`
**Behavior:**
1. Evaluate task complexity
2. Select model tier: haiku / sonnet / opus
3. Scan conversation history for existing agent IDs
4. Resume via `Agent(resume=id)` or initialize new subagent
5. Return result to user
**Examples:**
- `/route znajdź wszystkie pliki zawierające useState` → Haiku
- `/route zaimplementuj OAuth2 login` → Sonnet
- `/route zdebuguj memory leak w worker thread` → Opus
---
## /agents
Show status of persistent subagents in the current session.
**Usage:** `/agents`
**Behavior:** Scan conversation history and report:
- `haiku_id`: `<id>` or `not initialized`
- `sonnet_id`: `<id>` or `not initialized`
- `opus_id`: `<id>` or `not initialized`
Useful to verify which subagents are already running and can be resumed without re-initialization.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |