- Home
- Skills
- Workflow Automation
- Herdr Master
Works with the AI Agents you already use
Herdr Master
Persistent root orchestrator for Herdr: delegate several coding jobs to isolated worktrees and tabs, review the diff, squash-merge. Requires Herdr + AiHead CLI.
$5
Herdr Master
Example session with this skill installed
/herdr-master Add OAuth login, and separately fix the failing CSV export tests
- Read your context and instructions
- Compiled the herdr master
(Illustrative) Two child tabs opened, each in its own worktree. Plan approvals relayed to you. Final diff review per job, then a squash merge into develop and cleanup.
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.
Run a squad of coding agents from one chat
Herdr Master keeps one root session free while every job runs in its own Herdr tab and isolated git worktree.
- Delegates each task to a child agent (agy, pi, claude, opencode, hermes), never touching your main working tree.
- Monitors children with async watchers instead of polling loops.
- Asks you for technical decisions, plan approvals and direction when trade-offs appear.
- Runs a mandatory final review gate on the cumulative diff, then squash-merges approved work.
- Adopted workspaces are never closed and
git reset --hardis never used.
Why it matters
You stay in control of decisions while several jobs progress in parallel, each isolated and reviewed. Intended benefits, not measured gains; more agents mean more cost.
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
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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
Permissions
File Scopes
Runs herdr/herdm CLI commands locally. No network calls, no credential access. Never pushes.