Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Council

    1

    Multi-agent planning council in Herdr: independent member plans, cross-review, synthesis cycles and a consensus or vote. Requires Herdr + AiHead CLI.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    AI Council

    AI Council

    Example session with this skill installed

    /council Design the sync strategy for offline-first mobile with conflict resolution

    • Read your context and instructions
    • Compiled the ai council

    (Illustrative) 3 members draft plans, cross-review in 2 cycles, consensus reached; final_plan.md with decisions and dissent noted.

    final_plan.md

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

    About this skill

    Requires Herdr + the AiHead-Orchestrator CLI (free, MIT: github.com/pank85/AiHead-Orchestrator). Works only inside a Herdr workspace.

    Several independent plans. One consensus.

    AI Council gets diverse planning agents to draft separate plans, then challenge each other before you commit to one.

    1. Scout discovers the repo facts.
    2. Members draft independent plans (Round 0).
    3. Cross-review: each member critiques its peers.
    4. Synthesis cycles (max 5) revise plans on the collective feedback.
    5. Consensus check or a one-round vote picks the final plan.
    6. Final plan written to final_plan.md.

    Why it matters

    Independent drafts and cross-review surface blind spots before any code is written. Best for architecture decisions, not trivial tasks. Intended benefit, not a measured gain; more members cost more.

    Requirements

    Herdr (herdr.dev) and the AiHead-Orchestrator CLI. See the requirements section and the GitHub repo.

    Honest limits

    Requires Herdr and the AiHead-Orchestrator CLI; it does not run in a plain terminal or chat-only agent. Not tested end-to-end on every harness. Multiple agents use more tokens than a single-agent run. Product default models are catalog-resolved and need your own access to them (or pin yours with --models).

    Requires Herdr and the AiHead-Orchestrator CLI; it does not run in a plain terminal or chat-only agent. Not tested end-to-end on every harness. Multiple agents use more tokens than a single-agent run. Product default models are catalog-resolved and need your own access to them (or pin yours with --models).

    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

    Herdr v0.9.5+ (herdr.dev)
    AiHead-Orchestrator CLI (aihead/herdm)
    Python 3.10+ and uv
    Git repository
    Git

    Permissions

    File Scopes

    Git
    worktrees
    and
    run
    directories
    in
    your
    repo

    Runs herdr/herdm CLI commands locally. No network calls, no credential access. Never pushes.

    Listed5 days ago
    Updatedtoday

    What's inside

    Frequently Asked Questions

    No. Herdr (herdr.dev) and the AiHead-Orchestrator CLI are hard prerequisites. The skill stops with an actionable error if either is missing.

    Install Herdr from herdr.dev, then clone github.com/pank85/AiHead-Orchestrator (MIT) and run `uv pip install -e .`. Verify with `aihead --help`.

    The default squad is resolved from the CLI catalog and needs your own access to those models. You can pin your own with --models.

    No. Work lands as a squash commit locally; pushing is never automatic.

    New in Workflow Automation