Skip to content
Back to skills

Agentgrid Orchestrate

ASecurity

Hand out and track work across a running agentgrid. Send a prompt to one pane, inject a long mission file, broadcast to every pane, read a pane's output and watch live status. Use after a grid is running, when the user says "send this to pane 3", "broadcast", "inject the mission", "what is pane 2 doing" or "monitor the grid".

  • 9 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 20, 2026
ai-agentsgobash

Works with

  • mcp

Security analysis

A100/100

Scanned October 20, 2026

npx -y skills add naman10parikh/agentgrid --skill agentgrid-orchestrate --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agentgrid Orchestrate?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Agentgrid Orchestrate
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/naman10parikh-agentgrid-orchestrate/badge)](https://www.skillsdirectory.com/skills/naman10parikh-agentgrid-orchestrate)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: agentgrid-orchestrate
description: Hand out and track work across a running agentgrid. Send a prompt to one pane, inject a long mission file, broadcast to every pane, read a pane's output and watch live status. Use after a grid is running, when the user says "send this to pane 3", "broadcast", "inject the mission", "what is pane 2 doing" or "monitor the grid".
---

# agentgrid-orchestrate: hand out and track work

## When to use

- A grid is already running (created with `agentgrid ROWSxCOLS`, or the MCP tool `grid_create`).
- Each pane needs its own mission, or every pane needs the same instruction.
- You need to know which agents are working, waiting or done, without switching windows.

## Steps

1. **List the panes.** `agentgrid status --json` returns `{"panes":[{"ref","status","label","command"}]}`. Use the
   `ref` (for example `agentgrid:1.3`) or a pane id such as `%42` as the target.
2. **Send one prompt to one pane:**

   ```bash
   agentgrid send %42 "You are Builder 1. Implement the login form in src/auth/."
   ```

3. **Inject a long mission** (a Markdown file) into one pane:

   ```bash
   agentgrid inject %42 --file missions/builder-1.md
   ```

4. **Broadcast** the same line to every pane in the current window:

   ```bash
   agentgrid broadcast "Pull main, run the tests, then report what failed."
   ```

5. **Read and watch.** `agentgrid read %42 -n 40` prints the pane's last 40 lines. `agentgrid monitor` shows every
   pane's status and recent output, refreshed live. `agentgrid status` gives a one-shot summary.
6. **Follow-ups go to the owner.** When a pane's work produces a follow-up bug, send it to that same pane with
   `agentgrid send`. Do not broadcast it: the owner already holds the context.

From another coding agent, the same steps are MCP tools: `grid_status`, `pane_send`, `pane_inject`,
`grid_broadcast`, `pane_read` and `grid_dashboard` (run `agentgrid-mcp`, or install the plugin).

## Output

Every pane has its mission, and you can report each pane's state. Report back to the user: which mission went to
which pane, and the latest status of each (WORKING, WAITING, DONE or IDLE).

## Do not

- Never `tmux select-pane`: it steals the user's focus.
- Never inject missions before the panes are named: names are how you and the user tell the work apart.
- Never send a secret (a key, a token) in a prompt: agents read keys from environment variables.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.