Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Orchestra Board

    1

    A tiered task orchestrator that routes coding sub-tasks to the cheapest viable Claude model with a live status board.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Orchestra Board

    Orchestra Board

    Example session with this skill installed

    Add a CSV export to the reports page, cover it with tests, and update the README. Use the orchestra board.

    • Read your context and instructions
    • Compiled the orchestra board
    • Generated the data export

    Here is the plan. The Orchestra board pane will show each worker live as it runs.

    Plan

    #TaskTierAcceptance checkDepends on
    1Add toCsv() in src/reports/export.ts and an Export CSV button on the reports pagestandard (Sonnet)npm test -- export passes, the button downloads report.csvnone
    2Escape commas, quotes and line breaks in CSV fieldslight (Haiku)the 6 cases in export.test.ts pass1
    3Add an "Export to CSV" section to README.mdlight (Haiku)the section exists and npm run lint:md passes1

    Execution

    Task 1, Sonnet: SUCCESS. I re-ran npm test -- export myself: 4/4 passing.

    Task 2, Haiku: FAILED.

    I reverted export.ts to the end of task 1 and sent the task one tier up with the failure reason and "do not repeat this approach".

    Task 2, Sonnet: SUCCESS. My re-run: 6/6 passing.

    Task 3, Haiku: SUCCESS. The README section is added and npm run lint:md is clean.

    Escalation log

    TaskAttempts (Haiku > Sonnet > Opus)Final statusReason for each failure
    1. CSV exportSonnetSUCCESSnone
    2. Field escapingHaiku > SonnetSUCCESSHaiku: quotes not doubled
    3. READMEHaikuSUCCESSnone

    Summary

    • Files changed: src/reports/export.ts, src/reports/ReportsPage.tsx, src/reports/export.test.ts, README.md
    • All checks verified by me, not just reported by the workers. No task needed Opus.

    Next steps: try the button on a report that has many rows. Ask "what did my work cost this month?" for the 30-day token and cost report.

    report.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    Stop burning expensive Opus tokens on boilerplate and formatting. Most coding tasks don't require the most powerful model, but manual switching is a friction point that slows you down.

    This skill implements a hierarchical routing protocol that treats Claude as an orchestrator. It automatically offloads mechanical tasks to Haiku, standard features to Sonnet, and reserves Opus strictly for complex architectural logic or deep debugging.

    What it does

    • Tiered Routing automatically assigns tasks to Haiku, Sonnet, or Opus based on complexity.
    • Failover Escalation detects task failures and automatically retries with a higher-tier model.
    • Visual Task Tracking provides a side pane showing worker status, tool calls, and elapsed time.
    • Cost Monitoring generates 30-day token and dollar estimates across all projects.
    • Acceptance Verification mandates specific commands or checks to validate subagent output.

    How it works

    1. Plan the request into a task table defining tiers (light, standard, deep) and acceptance checks.
    2. Delegate work to subagents via the Agent tool using model-specific tiers.
    3. Monitor progress via the live board plugin or the terminal status report.
    4. Escalate failed tasks by reverting files and retrying on the next model tier.
    5. Review the 30-day cost report by running the included Node.js utility.

    Frameworks & tools

    Built for Claude Code (2.1.316+). Requires Node.js 18+ for cost reporting. The visual board is optimized for the Claude desktop app but supports terminal fallback.

    Installation

    1. Unzip the skill. Create the folder ~/.claude/skills/orchestra-board/ and unzip orchestra-board.zip into it, so that SKILL.md sits directly inside (next to the plugin folder). On Windows the folder is C:\Users\<you>\.claude\skills\orchestra-board\. Claude picks up the skill on its own.
    2. Install the board. In a terminal, run: On Windows, use the full path instead of ~, for example: claude plugin marketplace add "C:\Users\<you>\.claude\skills\orchestra-board\plugin"
    3. Reload. Restart Claude Code, or run /reload-plugins in an open session. The board opens at the start of every session, and /board reopens it.
    4. Optional: to apply the protocol to every coding task without asking, add this line to ~/.claude/CLAUDE.md: For multi-step coding tasks, follow the orchestra-board skill.

    To turn the board off: claude plugin disable orchestra-board@orchestra. To remove it: claude plugin uninstall orchestra-board@orchestra, then delete the skill folder.

    Why this beats prompting it yourself

    Manual model switching is tedious and often forgotten, leading to wasted spend on simple edits. This skill bakes the "start cheap, escalate on failure" logic into the agent's core loop, ensuring consistent cost-efficiency without manual intervention.

    Use cases

    • Large Refactors where formatting and renames go to Haiku while logic stays on Sonnet.
    • Cost Auditing to see exactly how many tokens your projects consumed over the last month.
    • Parallel Feature Dev by running independent sub-tasks across different model tiers simultaneously.

    Known limitations

    The board plugin needs a one-time install from the terminal (two commands, see Installation). Cost reporting relies on list-price assumptions and transcript file availability.

    Requires Claude Code 2.1.316+ and Node.js 18+. Cost reports are estimates based on list prices. Destructive tasks require manual confirmation before escalation.

    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 today

    Requires

    Node.js

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listedtoday

    What's inside

    Frequently Asked Questions

    Orchestra Board automates model selection by routing simple tasks like boilerplate to Claude Haiku and standard coding to Sonnet, reserving the expensive Opus model only for complex logic. This "start cheap, escalate on failure" approach can significantly reduce your API spend compared to using a single high-tier model for everything.

    It is specifically designed for Claude Code (v2.1.316 or newer). The visual status board is optimized for the Claude desktop application, though it includes a robust fallback for users working primarily in a terminal environment.

    The package includes the hierarchical routing protocol, the live status board plugin, a Node.js utility for 30-day cost auditing, and comprehensive setup documentation. It provides everything needed to transition from manual prompting to automated multi-tier orchestration.

    If a sub-task fails an acceptance check or returns an error, the skill automatically reverts any file changes and escalates the task to a higher-tier model for a retry. This ensures that cost-saving measures never compromise the final quality of your code.

    Installation requires a few terminal commands to link the board plugin and the Node.js cost reporter. While the core routing logic works immediately after activation, you will need Node.js 18+ installed on your machine to generate the 30-day usage and spend reports.

    New in Agents & Orchestration