mcpField
I
intelligence-route

intelligence-route

github.com/ruvnetAgent workflows80.0k741 installsUpdated today
Repository

About intelligence-route

A routing skill that selects an agent and model tier for a task using learned patterns and predictions. It is intended for teams delegating non-trivial work and provides an auditable rationale; recorded outcomes help train the router.

Key features

  1. 01Recommend an agent
  2. 02Recommend a model tier
  3. 03Search similar past patterns
  4. 04Predict outcomes with confidence
  5. 05Explain routing rationale
  6. 06Record outcomes to train the router

Use cases

  1. 01Select an agent before complex work
  2. 02Choose a model tier by task complexity
  3. 03Review and improve routing decisions

MCP support

It uses Ruflo hooks for agent and model routing, pattern search, prediction, explanations, and outcome recording. Routing commands are also available through @claude-flow/cli.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ruvnet/ruflo --skill intelligence-route

After installing, type/intelligence-routein Claude Code to confirm it loaded.

Details

From the project README

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__plugin_ruflo-core_ruflo__hooks_route with the task description. Returns { recommended, confidence, reasoning }.
  2. Get a model tier recommendation — mcp__plugin_ruflo-core_ruflo__hooks_model-route for Haiku/Sonnet/Opus selection.
  3. Search for similar past patterns — mcp__plugin_ruflo-core_ruflo__hooks_intelligence_pattern-search to find prior successes.
  4. Predict outcome — mcp__plugin_ruflo-core_ruflo__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__plugin_ruflo-core_ruflo__hooks_explain to surface the routing rationale to the user.
  7. After task completes — call mcp__plugin_ruflo-core_ruflo__hooks_model-outcome with success: true|false to train the router.

3-Tier Model Routing

TierHandlerLatencyCostWhen
1Deterministic codemod (TS compiler)~1ms$0Structural transforms with no LLM: var-to-const, remove-console, add-logging
2Haiku~500ms~$0.0002Low complexity (<30%), bug fixes, quick patches
3Sonnet/Opus2–5s$0.003–$0.015Complex 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__plugin_ruflo-core_ruflo__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"

Comments

Markdown supported