Stats
Actions
Tags
From next-task
Classifies tasks by cognitive tier (sm0l/ch0nky/frontier) and routes to optimal model from b00t config, preferring local/cheap for mechanical work and frontier for reasoning. Checks resources.
How this skill is triggered — by the user, by Claude, or both
Slash command
/next-task:model-routingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
NEVER use frontier model for mechanical work. Route by cognitive tier.
NEVER use frontier model for mechanical work. Route by cognitive tier.
Reads routing table from _b00t_/model-routing.tomllm. Falls back to hardcoded tiers.
| Tier | Tasks | b00t Models (in priority order) |
|---|---|---|
small (sm0l) | grep, lint, classify, route, test pass/fail | haiku, local sm0l |
chunky (ch0nky) | implement, refactor, debug, code review | qwen3-coder-local (RTX 3090), sonnet |
frontier | architecture, security, novel design, planning | opus, sonnet |
b00t learn model-routing via MCP or CLI — NEVER read .tomllm directly. # output: available_models[]b00t hive status — ensure RAM/GPU available. # output: resource_ok{model, tier, rationale} for caller to invoke.small sm0l (Haiku / local 3B):
chunky ch0nky (qwen3-coder-local → Sonnet fallback):
frontier (Opus → Sonnet fallback):
Executive context is costly. Sub-agents MUST return compressed summaries:
| Tier | Max output to executive |
|---|---|
sm0l | PASS or FAIL: <name> <5 lines> |
ch0nky | diff + test result (no full file dumps) |
frontier | structured decision with rationale |
Before invoking ch0nky/frontier check hive:
b00t hive status # output: RAM free, GPU VRAM free, active profile
Anti-pattern: running vLLM (qwen3-coder, 20GB VRAM) + HuggingFace download simultaneously on 24GB.
Used by /next-task at each phase to select model.
Used by b00t-mcp agent delegation.
Load via: b00t learn model-routing (MCP preferred, CLI fallback)
npx claudepluginhub elasticdotventures/_b00t_ --plugin next-taskRoutes tasks to Haiku, Sonnet, or Opus based on complexity to optimize cost and quality. Use for intelligent model selection and tiered routing.
Routes coding tasks to optimal AI model tier by complexity: no LLM for mechanical edits, Haiku for simple refactors, Sonnet for multi-file bugs, Opus for architecture/security. Saves 50-65% API costs.
Recommends Claude models (Haiku for exploration, Sonnet for implementation, Opus for decisions) via routing matrix for task types, subagents, and cost-quality tradeoffs.