Intelligence Route
- 646 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
intelligence-route is a Claude Flow skill that routes tasks through a 3-tier model selector and learned patterns, emitting routing rationale via hooks_explain for developers who need optimal agent and model choice per ta
About
intelligence-route is a RuFlo Claude Flow skill that routes tasks via a 3-tier model selector and learned patterns, emitting a routing rationale through hooks_explain. It connects to hooks_route, hooks_model-route, hooks_model-stats, hooks_model-outcome, hooks_intelligence_pattern-search, hooks_intelligence_attention, hooks_intelligence_stats, neural_predict, and hooks_pre-task to pick the optimal agent and model tier for each job. Developers pass a task description and optional --why flag when model choice affects cost, latency, or reasoning depth. The skill learns from prior outcomes stored in intelligence patterns rather than applying static model maps. Use intelligence-route at the start of non-trivial agent work in Claude Code when routing decisions should be explicit and auditable.
- Routes prompts intelligently across multiple Claude models or reasoning strategies
- Reduces token usage and cost by choosing the right intelligence level per task
- Supports parallel evaluation of different agent paths before committing
- Integrates directly with Cursor, Claude Code, and other agent runtimes
- 4 distinct routing modes: complexity-based, cost-optimized, quality-first, and hybrid
Intelligence Route by the numbers
- 646 all-time installs (skills.sh)
- +10 installs in the week ending Jul 26, 2026 (Skillselion tracking)
- Ranked #1,496 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill intelligence-routeAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 646 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you route tasks to the right LLM tier?
Dynamically select the optimal reasoning path, model, or workflow for any given task.
Who is it for?
Developers running claude-flow multi-model agent stacks who need learned, explainable routing before complex tasks.
Skip if: Developers on a single fixed model with no claude-flow hooks_route or intelligence pattern infrastructure.
When should I use this skill?
A task needs optimal agent and model tier selection, or the user requests routing rationale with --why.
What you get
Routing decision, model tier selection, agent assignment, and hooks_explain rationale output.
- routing decision
- explainable routing rationale
By the numbers
- Routes through a 3-tier model selector with learned intelligence patterns
Files
Intelligence Routing
Pick the optimal agent + model tier for a task using learned patterns + the 3-tier router. Emits a hooks_explain rationale so the choice is auditable.
When to use
Before starting any non-trivial task. Replaces manual agent selection with data-driven decisions.
Steps
1. Get an agent recommendation — mcp__claude-flow__hooks_route with the task description. Returns { recommended, confidence, reasoning }. 2. Get a model tier recommendation — mcp__claude-flow__hooks_model-route for Haiku/Sonnet/Opus selection. 3. Search for similar past patterns — mcp__claude-flow__hooks_intelligence_pattern-search to find prior successes. 4. Predict outcome — mcp__claude-flow__neural_predict with the task description for a confidence-scored prediction. 5. Spawn the recommended agent at the recommended model tier. 6. (If `--why` was passed) — call mcp__claude-flow__hooks_explain to surface the routing rationale to the user. 7. After task completes — call mcp__claude-flow__hooks_model-outcome with success: true|false to train the router.
3-Tier Model Routing
| Tier | Handler | Latency | Cost | When |
|---|---|---|---|---|
| 1 | Deterministic codemod (TS compiler) | ~1ms | $0 | Structural transforms with no LLM: var-to-const, remove-console, add-logging |
| 2 | Haiku | ~500ms | ~$0.0002 | Low complexity (<30%), bug fixes, quick patches |
| 3 | Sonnet/Opus | 2–5s | $0.003–$0.015 | Complex reasoning, architecture, security, multi-file refactors |
When hooks_route returns [CODEMOD_AVAILABLE] for a deterministic intent (var-to-const, remove-console, add-logging), call mcp__claude-flow__hooks_codemod with the intent + file — it applies the transform via the TypeScript compiler at $0, no LLM. Note: add-types, add-error-handling, async-await require judgement and route to a model (Tier 2/3) per ADR-143; they are NOT $0 codemods. Agent Booster is a fast-apply merge engine for LLM-produced edits, not the Tier-1 path.
Recording outcomes
Closing the routing loop is mandatory:
# Success
mcp tool call hooks_model-outcome --json -- '{"taskId": "T123", "success": true, "model": "haiku"}'
# Failure with reason
mcp tool call hooks_model-outcome --json -- '{"taskId": "T123", "success": false, "model": "haiku", "reason": "complexity-misjudged"}'The router learns from these calls. Skipping them = no learning.
CLI alternative
npx @claude-flow/cli@latest hooks route --task "description"
npx @claude-flow/cli@latest hooks pre-task --description "description"
npx @claude-flow/cli@latest hooks explain --topic "routing decision"Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Choose intelligence-route over static model maps when claude-flow hooks and learned patterns should drive per-task tier selection with explainable output.
FAQ
How does intelligence-route choose a model?
intelligence-route uses a 3-tier model selector plus learned patterns from hooks_intelligence_pattern-search and neural_predict. hooks_model-route and hooks_route assign the optimal agent and tier, with rationale via hooks_explain.
Can intelligence-route explain its routing decision?
intelligence-route supports a --why flag that triggers hooks_explain output. Developers receive an auditable rationale covering agent choice, model tier, and pattern matches before work proceeds.