Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Subagent Triage

    1

    Optimizes subagent costs and performance by routing tasks to the right Claude model and reasoning level.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Subagent Triage

    Subagent Triage

    Example session with this skill installed

    Start a subagent to scan the /src directory and list all files that don't have a corresponding test file in /tests.

    • Read your context and instructions
    • Compiled the subagent triage

    I have analyzed the subtask and determined the optimal resource allocation using the TypeSafe Jev model. The task is categorized as mechanical/local, requiring low reasoning effort and posing zero operational risk.

    Subagent triage: haiku / low. tier fast (0.88) · effort 0.08 (0.94) · risky 0.01

    Subagent Configuration

    ParameterSelected ValueRationale
    ModelhaikuTask is a simple file system inventory; high confidence in fast tier.
    EffortlowMinimal reasoning required for existence checks.
    RisklowRead-only operation; no production impact.

    Next steps

    1. Initiating the subagent with the haiku model to perform the directory scan.
    2. Reviewing the list of missing test files returned by the subagent.
    3. Deciding if a subsequent high-effort subagent is needed to generate the missing tests.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Standard agent delegation often wastes money by using high-end models for trivial tasks or fails by starving complex tasks of reasoning power. This skill implements an automated routing layer between your main agent and its subagents. It determines the optimal model tier and reasoning effort for every subtask before execution.

    What it does

    • Dynamic model selection maps subtasks to Haiku, Sonnet, or Opus based on task complexity.
    • Reasoning effort tuning adjusts reasoning levels from low to extra-high based on the cognitive load required.
    • Risk assessment automatically forces high-end models for production changes or high-stakes data operations.
    • Calibrated routing uses confidence thresholds to prevent down-sampling tasks without high certainty.
    • Customizable ladders allows developers to define their own model hierarchy and cost constraints in local config files.

    How it works

    1. Analyze subtasks by generating a concise title and description of the work without leaking sensitive data.
    2. Query a decision model (TypeSafe's Jev or Google's Gemini Decision) to score task difficulty, reasoning needs, and operational risk.
    3. Apply decision logic to compare the subtask requirements against the user's defined model ladder and confidence bars.
    4. Invoke subagents with specific model and effort parameters for the Claude Code Agent tool.

    Frameworks & tools

    Built for Claude Code. Uses a decision model via REST API: TypeSafe's Jev or Google's Gemini Decision (gemini-decision-1), whichever key you set. Jev is preferred when both are set. Supports local configuration through CLAUDE.md.

    Why this beats prompting it yourself

    Manual prompting for subagent routing is inconsistent and often ignored during deep task execution. This skill uses a dedicated decision model with calibrated confidence scores, ensuring cost savings and performance reliability are enforced mathematically rather than through vibes.

    Use cases

    • Cost optimization for large-scale code refactors where many subtasks are simple renames or documentation updates.
    • Security shielding for infrastructure tasks that require the highest reasoning capacity to avoid destructive errors.
    • Automated QA where test execution needs low effort but test architecture needs high effort.

    Known limitations

    Currently optimized for Claude Code. Support for Codex, OpenCode, and Cursor is limited to retrieving decisions without automated application. Requires a TypeSafe or Gemini API key.

    Optimized for Claude Code. Requires TYPESAFE_API_KEY. Other IDE agents like Cursor can see decisions but not yet apply them automatically. Data privacy checks skip routing for confidential info.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Requires

    Google AI
    Typesafe

    Permissions

    Terminal / Shell
    Network Access

    Allowed Hosts

    api.typesafe.ai
    generativelanguage.googleapis.com
    Listed18 days ago
    Updated5 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as an intelligent router that analyzes the complexity of each subtask to assign the most cost-effective Claude model (Haiku, Sonnet, or Opus) and reasoning level, preventing expensive models from being wasted on simple tasks.

    The skill is built specifically for Claude Code, utilizing the TypeSafe Jev decision model to automate routing; while other agents like Cursor can access the decision data, automated application is currently exclusive to Claude Code.

    Yes, you can define your own model hierarchy and cost constraints via local configuration files, allowing you to prioritize performance or budget based on your specific project needs.

    You will receive the core routing logic, integration scripts for Claude Code, and documentation for setting up your TypeSafe API key and local configuration.

    Setup involves integrating the skill into your Claude Code environment and providing a TypeSafe API key, which the router uses to calculate task difficulty and operational risk scores.

    The skill includes an automated risk assessment layer that identifies high-stakes operations, such as production changes, and automatically forces the highest reasoning tier to ensure safety and accuracy.

    New in Agents & Orchestration