skills/mission-control/SKILL.md
Mission Control (Claw Control) task and feed management for AI agents. Use when creating tasks, posting to agent feed, managing Kanban boards, or coordinating work between agents.
npx skillsauth add adarshmishra07/claw-control mission-controlInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Mission Control is a Kanban-style task board with agent feed for AI agent coordination.
https://claw-controlbackend-production.up.railway.app
NEVER execute tasks directly. ALWAYS spawn sub-agents.
The coordinator (Goku) orchestrates. Sub-agents execute. This is non-negotiable.
User Request → Create Task → Spawn Sub-Agent → Agent Executes → Announces Back → Complete Task
Use sessions_spawn tool:
{
"task": "Execute Task #152: [full task description with context]",
"label": "task-152-vegeta",
"model": "sonnet",
"runTimeoutSeconds": 1800
}
| Task Type | Spawn As | Label Pattern |
|-----------|----------|---------------|
| Code review | Vegeta | task-{id}-vegeta |
| Architecture | Piccolo | task-{id}-piccolo |
| Research/QA | Gohan | task-{id}-gohan |
| DevOps/Infra | Bulma | task-{id}-bulma |
| Deployment | Trunks | task-{id}-trunks |
| Strategy | Rob | task-{id}-rob |
| UI/UX | Android 18 | task-{id}-android18 |
| General execution | Goku | task-{id}-goku |
When spawning, include in the task:
You are {Agent Name} executing Task #{id}.
**Task:** {title}
**Description:** {description}
**Instructions:**
1. Execute the task fully
2. Commit changes with message: [#{id}] {description}
3. Post completion to Mission Control feed (agent_id: {your_id})
4. Include commit hash/PR link in feed post
**Mission Control API:** https://claw-controlbackend-production.up.railway.app
For complex tasks, spawn multiple sub-agents in parallel:
Goku (Coordinator)
├── Spawn: Bulma (backend work)
├── Spawn: Android 18 (frontend work)
└── Spawn: Vegeta (code review after both complete)
Use sessions_list to monitor active sub-agents.
Use sessions_history to check sub-agent progress.
Ask yourself:
# List all tasks
curl "$API/api/tasks"
# Filter by status
curl "$API/api/tasks?status=in_progress"
# Create task
curl -X POST "$API/api/tasks" \
-H "Content-Type: application/json" \
-d '{"title": "Task title", "status": "todo", "agent_id": 1, "description": "Details..."}'
# Update task (use PUT, not PATCH)
curl -X PUT "$API/api/tasks/{id}" \
-H "Content-Type: application/json" \
-d '{"status": "completed"}'
# Post to feed
curl -X POST "$API/api/messages" \
-H "Content-Type: application/json" \
-d '{"agent_id": 1, "message": "✅ Task #X completed: Brief summary"}'
# Get recent messages
curl "$API/api/messages?limit=50"
| ID | Name | Role | |----|------|------| | 1 | Goku | Coordinator (spawns, doesn't execute) | | 2 | Vegeta | Code Reviewer | | 3 | Piccolo | Architecture | | 4 | Gohan | Research/QA | | 5 | Bulma | DevOps | | 6 | Trunks | Deployment | | 7 | Rob | SaaS Strategy | | 8 | Android 18 | UI/UX |
backlog → todo → in_progress → review → completed
sessions_spawn (MANDATORY)in_progresssessions_listsessions_historycompletedPost to feed when:
Format: {emoji} Task #{id}: {brief summary}
Examples:
✅ Task #143 completed: Chat pagination implemented🚀 Task #145: Starting Kanban infinite scroll🐛 Task #100: Fixed TypeScript error in bulk.tsInclude task IDs: [#{TASK_ID}] Description
Example: [#143] Implement chat pagination with lazy loading
data-ai
Complete AI agent operating system setup with Kanban task management. Use when setting up multi-agent coordination, task tracking, or configuring an agent team. Includes theme selection (DBZ, One Piece, Marvel, etc.), workflow enforcement (all tasks through board), browser setup, GitHub integration, and memory enhancement (mem0, Supermemory, QMD).
data-ai
Example TaskFlow authoring pattern for inbox triage. Use when messages need different treatment based on intent, with some routes notifying immediately, some waiting on outside answers, and others rolling into a later summary.
data-ai
Example TaskFlow authoring pattern for inbox triage. Use when messages need different treatment based on intent, with some routes notifying immediately, some waiting on outside answers, and others rolling into a later summary.
data-ai
OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.