New to Claude Skills? Learn how to install them →

Cruvnet on GitHub

Cost Booster Route

Free

Optimize task routing for zero-cost transformations.

by ruvnet67.6k stars on ruvnet/ruflo
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Cost Booster Route does

Cost Booster Route is a skill designed to enhance the efficiency of task management by utilizing the mcp__plugin_ruflo-core_ruflo__hooks_route functionality. This skill focuses on identifying tasks eligible for Tier 1 processing, which allows for execution without any associated costs. By routing tasks through the agent booster, users can leverage WASM transforms that do not require LLM calls, effectively achieving a structural cost of $0. The skill is particularly useful for developers and designers who frequently handle batches of similar tasks and want to minimize expenses while maximizing efficiency.

The process begins with collecting tasks, either through a single argument or by fetching recent entries from the cost-tracking memory. Users can analyze up to 50 tasks at a time, which are then routed through hooks_route. The responses are partitioned based on whether they qualify for Tier 1 processing, allowing users to see how many tasks can be executed without cost. This partitioning also provides insights into the types of transformations being performed, such as variable conversion or error handling, enabling users to make informed decisions about their task management strategies.

One of the key features of Cost Booster Route is its reporting capability. After processing, users receive a detailed report that outlines the number of tasks analyzed, how many qualified for the Tier 1 bypass, and the potential costs associated with Tier 2 and Tier 3 tasks. This transparency allows users to track their usage and optimize future task routing. Additionally, the skill persists this data for future reference, ensuring that users can keep track of their cost-saving measures over time.

Overall, Cost Booster Route is an essential tool for those looking to streamline their task management processes while keeping costs at bay. It is particularly beneficial in scenarios where tasks can be transformed simply and efficiently, making it a valuable addition to any developer or designer's toolkit.

When to use it

Use this skill before processing a batch of similar tasks or when previous cost reports indicate high spending on simple transformations.

When not to use it

This skill may not be suitable for tasks that require complex LLM interactions or when the upstream router does not reliably classify tasks as Tier 1.

What you can build with it

Batch Processing for Code Refactoring

Use this skill before refactoring code to identify which tasks can be executed at zero cost.

Cost Analysis for Automation Tasks

Employ Cost Booster Route to analyze costs associated with automating repetitive tasks and optimize spending.

Reporting on Task Efficiency

Generate reports to track how many tasks qualify for zero-cost processing and adjust strategies accordingly.

How to install Cost Booster Route

View source

1. Install with the skills CLI

npx skills add ruvnet/ruflo/cost-booster-route --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by ruvnet

Cost Booster Route

Wraps mcp__plugin_ruflo-core_ruflo__hooks_route and reports how many tasks the 3-tier router classified as Agent Booster (Tier 1) eligible. Tier 1 bypasses run as WASM transforms — no LLM call, structurally $0 cost.

When to use

Before a batch of similar tasks, or when cost-report shows Sonnet/Opus spend on descriptions that look like simple transforms (var-to-const, add-types, add-error-handling, async-await, add-logging, remove-console).

Steps

  1. Collect tasks — single arg or recent entries from cost-tracking via memory_search. Cap batch at 50.

  2. Route each — call hooks_route with the description; capture the full response string.

  3. Partition — group by whether the response contains the literal [AGENT_BOOSTER_AVAILABLE] (Tier 1) vs. not (Tier 2/3). Extract [TASK_MODEL_RECOMMENDATION] Use model="X" when present.

  4. Compute spend — Tier 1 partition: $0. Tier 2/3 partition: per-task upper-bound from REFERENCE.md pricing × recommended model.

  5. Report

    === Booster bypass report ===
    Tasks analyzed:        50
    Tier 1 (booster):      18 (36%)  — $0.00
    Tier 2/3 (LLM):        32 (64%)  — $X.XX (upper-bound)
    Booster intents:       var-to-const (8), add-types (5), remove-console (5)
    
  6. Persistmemory_store --namespace cost-tracking --key "booster-route-$(date +%Y%m%d-%H%M%S)" --value '{"tier1": N, "tier2_or_3": M, ...}' so cost-report picks up the tier signal.

Caveats — claimed upstream, not yet verified

  • [AGENT_BOOSTER_AVAILABLE] fires only when the upstream router populates routeResult.agentBoosterIntent.type (v3/@claude-flow/cli/src/mcp-tools/hooks-tools.ts:1228). The published CLI's semantic-VectorDb path does not always trigger the classifier — treat the partition as a lower bound on Tier 1 eligibility.
  • CLAUDE.md root claims <1ms latency and 352× faster than LLM. <1ms and $0 are structural; 352× is claimed upstream, not yet verified here. Report what the router actually returns.
  • See docs/benchmarks/0002-baseline.md for the full upstream-claims-vs-measured table.

Cross-references

ADR-0002 Decision #1 · ruflo-intelligence ADR-0001 §"Neutral" (closes the routing-outcomes loop via cost-optimize step 8) · CLAUDE.md root §"3-Tier Model Routing (ADR-026)".

Frequently asked questions about Cost Booster Route

Similar skills