More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Opus Delegate for Claude Code

    2

    Stretch your Claude Code weekly limit: heavy work like features, refactors and long docs goes to Opus subagents automatically, while your top model keeps planning and review.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Opus Delegate for Claude Code

    Opus Delegate for Claude Code

    Example session with this skill installed

    Add a "forgot password" flow to my FastAPI app: reset link by email, one-time tokens that expire, rate limiting, and tests. Keep all the existing tests green and restart the server when done.

    • Read your context and instructions
    • Compiled the opus delegate

    Summary

    Real session, lightly trimmed. The orchestrator (Fable 5) turned the request into a detailed handoff brief and spawned one Opus worker. The worker built and tested the whole feature in about 3 minutes with 16 tool uses, all on Opus. The orchestrator only read the report below and reviewed it.

    ⏺ Agent(general-purpose, model: opus) · Build password reset flow
      ⎿ Done (16 tool uses · 2m 52s)
    

    Worker report

    I've added a forgot-password flow that resets by email. All tests pass, the live server was restarted, and it's committed.

    What was added

    PieceWhat it does
    Login pageNew "Forgot your password?" link
    /forgot-passwordOne email field with CSRF. Real and unknown emails get the same page, and the email is sent after the response, so neither the page nor the timing reveals whether an account exists. Limited to 3 requests per hour per address and 10 per IP.
    Reset emailOne line saying what to do, the link, then "If you did not ask for this, you can ignore this email. The link stops working in 2 hours."
    TokensStored hashed in a new reset_tokens table, valid for 2 hours, usable once. Using one cancels every other open link for that user.
    /reset-passwordValid link: new password and repeat fields with the same live checklist as sign-up. Bad or expired link: a friendly page with a "Send me a new link" button.
    SessionsEvery session from before the reset stops working, through a new pw_changed_at column checked on each request.

    Decisions beyond the brief

    1. Reset tokens got their own table, because the existing confirmation code deletes all of a user's rows in the shared one, which would wipe reset links.
    2. A reset also confirms the email address, since clicking the link proves ownership.
    3. A reset clears the login lockout, so a locked-out user can log in straight away.
    4. The password checklist moved into a shared template used by both sign-up and reset.

    Tests: 59 passed (the 55 existing plus 4 new), covering identical responses for real and unknown emails, the full request-to-login flow, used, expired and made-up links, weak and mismatched passwords, the old session dying, and rate limits.

    Server: restarted. /, /forgot-password and /login return 200, and a bogus reset link returns its friendly 400 page.

    Next steps

    1. Deploy as usual. Only the 8 files the worker touched were committed.
    2. Known trade-off: each new request issues another link without cancelling earlier ones, so a delayed first email still works. All open links die as soon as one is used.

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

    About this skill

    Claude Code meters its top tier models with tight weekly limits. If your best model types every line of code itself, the cap is gone by Wednesday. Claude Code can already spawn subagents on Opus, and Opus handles implementation work very well. Nothing makes that the default. This skill does.

    What it does?

    1. Your orchestrating model keeps the thinking: planning, review and the final answer.
    2. Heavy self-contained work (features, refactors, research across many files, long docs) is handed to an Opus subagent instead of running inline.
    3. It routes the specialist agents you already have too, by spawning them with the Opus override. No need to edit any of their files.
    4. Quick two minute edits stay inline on purpose, so you never wait on a subagent for a one-liner.

    What's inside

    PieceWhat it does
    SKILL.mdThe delegation rule plus how to write a good handoff prompt
    agents/opus-worker.mdA generic worker agent pinned to Opus, installed on first use
    scripts/opus.jsOptional opus terminal command: interactive Opus session, or a one-shot answer

    Real numbers from two sessions

    Session A (6 days)Session B (10 days)
    Output written by the orchestrator (Fable 5.1)0.59M tokens (24%)2.8M tokens (16%)
    Output written by Opus workers1.83M tokens (76%)14.3M tokens (81%)
    Tasks handed to Opus44
    Code changed57,147 lines added

    Across both sessions, about four of every five tokens written came from Opus. The top tier model spent its share on planning, writing handoffs and reviewing reports.

    Why trust it?

    No binaries, no API keys, no server, nothing running in the background. It uses documented Claude Code features (model pinning in agent files and per-agent model overrides). Every file reads in a minute, and removing it takes a minute.

    Roadmap

    Today the skill works in Claude Code only. The same idea, a top model that plans and reviews while a cheaper model's subagents do the heavy work, can carry over to other agents that support subagents with their own model choice. Planned next:

    1. Codex CLI: route heavy work from the top model to cheaper Codex subagents.
    2. Other agents with subagent support, such as Gemini CLI and Cursor, as their subagent features allow.

    Buyers get every future version of this skill at no extra cost.

    1. Claude Code only. It does not work in regular Claude chat, because chat cannot start Opus subagents.
    2. The delegation is an instruction the model follows, not a hard router. Models follow it well, but nothing enforces it.
    3. Quick two minute edits stay on your main model on purpose.
    4. It shifts usage to Opus rather than removing it. Opus work still counts toward your all-models weekly limit.
    5. The worker does not see your conversation, so tasks that depend on a long chat history stay inline.
    6. The opus-worker agent is installed on first use and becomes available from the next session.

    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 19 days ago

    Requires

    Claude Code

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Write access is used once, to copy the opus-worker agent into ~/.claude/agents on first use. Shell is only used by the optional opus command, which launches the claude CLI with the Opus model. No network calls, no environment variables, no API keys.

    Listed19 days ago

    What's inside

    Frequently Asked Questions

    It makes your top tier Claude Code model hand heavy, self-contained tasks to Opus subagents, so your scarce weekly quota goes to planning and review instead of typing.

    Claude Code: in the terminal on Windows, macOS, Linux and WSL, and in the Code tab of the Claude desktop app. It does not work in regular Claude chat, because chat cannot start Opus subagents.

    Install the skill and work as usual. When a task will take more than a couple of tool calls, the orchestrator spawns an Opus worker and reviews its report. On first use it copies the opus-worker agent into ~/.claude/agents.

    It shifts it, which is the point. The heavy spend moves to Opus and the orchestrator only reads worker reports. How much that saves depends on how your plan meters each model, so watch /usage for a week.

    No. Pinning a model in an agent file and overriding the model per subagent are normal Claude Code features.

    The opus alias resolves to the latest Opus model, so the skill follows along with no changes.

    New in Agents & Orchestration