Intelligence Route

What it does

When your agent uses it

• Development work in your project

Example prompts

• “/intelligence-route”

Requirements

• Node.js
• Pre-approved tools (allowed-tools): mcp__plugin_ruflo-core_ruflo__hooks_route, mcp__plugin_ruflo-core_ruflo__hooks_explain, mcp__plugin_ruflo-core_ruflo__hooks_model-route, mcp__plugin_ruflo-core_ruflo__hooks_model-stats, mcp__plugin_ruflo-core_ruflo__hooks_model-outcome, mcp__plugin_ruflo-core_ruflo__hooks_intelligence_pattern-search, mcp__plugin_ruflo-core_ruflo__hooks_intelligence_attention, mcp__plugin_ruflo-core_ruflo__hooks_intelligence_stats, mcp__plugin_ruflo-core_ruflo__neural_predict, mcp__plugin_ruflo-core_ruflo__hooks_pre-task, Bash

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Get an agent recommendation — mcpplugin_ruflo-core_ruflohooks_route with the task description. Returns { recommended, confidence…
2. 2Get a model tier recommendation — mcpplugin_ruflo-core_ruflohooks_model-route for Haiku/Sonnet/Opus selection.
3. 3Search for similar past patterns — mcpplugin_ruflo-core_ruflohooks_intelligence_pattern-search to find prior successes.
4. 4Predict outcome — mcpplugin_ruflo-core_rufloneural_predict with the task description for a confidence-scored prediction.
5. 5Spawn the recommended agent at the recommended model tier.
6. 6(If --why was passed) — call mcpplugin_ruflo-core_ruflohooks_explain to surface the routing rationale to the user.
7. 7After task completes — call mcpplugin_ruflo-core_ruflohooks_model-outcome with success: true|false to train the router.

What it can do on your machine

Read from SKILL.md and the folder at commit de590e1. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • mcp__plugin_ruflo-core_ruflo__hooks_route
  • mcp__plugin_ruflo-core_ruflo__hooks_explain
  • mcp__plugin_ruflo-core_ruflo__hooks_model-route
  • mcp__plugin_ruflo-core_ruflo__hooks_model-stats
  • mcp__plugin_ruflo-core_ruflo__hooks_model-outcome
  • mcp__plugin_ruflo-core_ruflo__hooks_intelligence_pattern-search
  • mcp__plugin_ruflo-core_ruflo__hooks_intelligence_attention
  • mcp__plugin_ruflo-core_ruflo__hooks_intelligence_stats
  • mcp__plugin_ruflo-core_ruflo__neural_predict
  • mcp__plugin_ruflo-core_ruflo__hooks_pre-task

  …and 1 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Intelligence Route loads about 874 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 254 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~32

When it runs · the whole SKILL.md, loaded when a task matches

~874

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: mcp__plugin_ruflo-core_ruflo__hooks_route, mcp__plugin_ruflo-core_ruflo__hooks_explain, mcp__plugin_

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ruvnet/ruflo at commit de590e1, republished under its MIT licence (© ruvnet). 254 words, ~874 tokens.

name

intelligence-route

description

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

allowed-tools

mcp__plugin_ruflo-core_ruflo__hooks_route, mcp__plugin_ruflo-core_ruflo__hooks_explain, mcp__plugin_ruflo-core_ruflo__hooks_model-route, mcp__plugin_ruflo-core_ruflo__hooks_model-stats, mcp__plugin_ruflo-core_ruflo__hooks_model-outcome, mcp__plugin_ruflo-core_ruflo__hooks_intelligence_pattern-search, mcp__plugin_ruflo-core_ruflo__hooks_intelligence_attention, mcp__plugin_ruflo-core_ruflo__hooks_intelligence_stats, mcp__plugin_ruflo-core_ruflo__neural_predict, mcp__plugin_ruflo-core_ruflo__hooks_pre-task, Bash

argument-hint

<task-description> [--why]

# 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"}'

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"

© ruvnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/ruflo-intelligence/skills/intelligence-route of ruvnet/ruflo.

Open the folder on GitHubat commit de590e1