Skip to main content
AI/MLruvnet

intelligence-route

Route tasks via the 3-tier model selector and learned patterns; emits a routing rationale via hooks_explain

Stars
56,726
Source
ruvnet/claude-flow
Updated
2026-05-31
Slug
ruvnet--claude-flow--intelligence-route
View on GitHubRaw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/ruvnet/claude-flow/HEAD/plugins/ruflo-intelligence/skills/intelligence-route/SKILL.md -o .claude/skills/intelligence-route.md

Drops the SKILL.md into .claude/skills/intelligence-route.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

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"