Skip to content
Back to skills

Mobilize

ASecurity

Multi-agent coordination protocol for tasks spanning 3+ distinct domains. Decomposes goal into sub-tasks, spawns specialized agents in isolated worktrees, aggregates results.

  • 11 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added June 6, 2026
ai-agentspythongobashcode-review

Security analysis

A100/100

Scanned June 6, 2026

npx -y skills add senda-labs/DQIII8 --skill mobilize --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mobilize?

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

Security grade badge for Mobilize
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/senda-labs-mobilize/badge)](https://www.skillsdirectory.com/skills/senda-labs-mobilize)

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: mobilize
description: Multi-agent coordination protocol for tasks spanning 3+ distinct domains. Decomposes goal into sub-tasks, spawns specialized agents in isolated worktrees, aggregates results.
command: /mobilize
allowed-tools: [Bash, Read, Write, Glob, Grep]
user-invocable: true
---

# /mobilize — Multi-Agent Coordination Protocol

## Trigger Conditions
- User invokes `/mobilize`
- User says "coordinate" + describes 3+ distinct domains
- Task touches 3+ unrelated domains simultaneously

## Protocol

### Step 1 — Decompose (Orchestrator, Plan Mode)
1. Enter plan mode immediately.
2. Break the goal into sub-tasks, one per domain/concern.
3. Write decomposition to `tasks/todo.md` under **Queued**.
4. Write agent assignments to `tasks/status.md` (format below).
5. Maximum 5 parallel agents.

### Step 2 — Spawn Agents
For each sub-task:
- Spawn a Task agent with the appropriate agent type (see CLAUDE.md Delegation table).
- Pass only the minimum context needed for that sub-task.
- Every agent gets an isolated worktree (`isolation: worktree`).
- Each agent writes its result to `tasks/results/{agent_name}-{YYYY-MM-DD}.md`.
- Agents NEVER write to `tasks/todo.md`.

### Step 3 — Monitor
- Poll `tasks/results/` until all expected result files appear.
- Update `tasks/status.md` as agents complete.
- If an agent fails or times out, note in `tasks/status.md` and re-spawn once.

### Step 4 — Aggregate
- Read all result files from `tasks/results/`.
- Synthesize into a final summary for the user.
- Move completed tasks in `tasks/todo.md` from **Queued/In Progress** → **Done**.
- Clean up `tasks/status.md`.

---

## tasks/status.md Format

```
# Mobilize Status — {goal summary}
Started: {timestamp}

| Agent | Sub-task | Status | Result file |
|-------|----------|--------|-------------|
| python-specialist | Refactor X | done | tasks/results/python-specialist-2026-03-11.md |
| code-reviewer | Review PR | running | — |
```

---

## Constraints
- Max 5 parallel agents.
- Each agent: isolated worktree at `/tmp/dqiii8-wt/{agent_id}`.
- Orchestrator does NOT share its context window with subagents.
- Destructive actions always require user confirmation before spawning agents.
- If decomposition is unclear, ask the user ONE clarifying question before proceeding.

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.