New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Mission Control Integration

Mission Control Agent Skill

by builderz-labs · MIT license · ★ 6,320 on GitHub

Mission Control Agent Skill cover

Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.

---
name: mission-control
description: "Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs."
---

# Mission Control Agent Skill

Mission Control (MC) is an AI agent orchestration dashboard with real-time SSE/WebSocket, a skill registry, framework adapters, and RBAC. This skill teaches agents how to interact with MC APIs programmatically.

## Quick Start

**Base URL:** `http://localhost:3000` (default Next.js dev) or your deployed host.

**Auth header:** `x-api-key: <your-api-key>`

**Register + heartbeat in two calls:**

```bash

Overview

Mission Control (MC) is an AI agent orchestration dashboard with real-time SSE/WebSocket, a skill registry, framework adapters, and RBAC. This skill teaches agents how to interact with MC APIs programmatically.

Manual install (npx, ZIP)
Claude Codenpx skills add builderz-labs/mission-control -g -a claude-code
Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md8.2 KB
Read SKILL.md here
builderz-labs/main1 file
SKILL.md
Show the full text278 lines

Mission Control Agent Skill

Mission Control (MC) is an AI agent orchestration dashboard with real-time SSE/WebSocket, a skill registry, framework adapters, and RBAC. This skill teaches agents how to interact with MC APIs programmatically.

Quick Start

Base URL: http://localhost:3000 (default Next.js dev) or your deployed host.

Auth header: x-api-key: <your-api-key>

Register + heartbeat in two calls:

# 1. Register
curl -X POST http://localhost:3000/api/adapters \
  -H "Content-Type: application/json" \
  -H "x-api-key: $MC_API_KEY" \
  -d '{
    "framework": "generic",
    "action": "register",
    "payload": { "agentId": "my-agent-01", "name": "My Agent" }
  }'

# 2. Heartbeat (repeat every 5 minutes)
curl -X POST http://localhost:3000/api/adapters \
  -H "Content-Type: application/json" \
  -H "x-api-key: $MC_API_KEY" \
  -d '{
    "framework": "generic",
    "action": "heartbeat",
    "payload": { "agentId": "my-agent-01", "status": "online" }
  }'

Authentication

MC supports two auth methods:

Method Header Use Case
API Key x-api-key: <key> or Authorization: Bearer <key> Agents, scripts, CI/CD
Session cookie Cookie: __Host-mc-session=<token> (HTTPS) or mc-session=<token> (HTTP) Browser UI

Roles (hierarchical): viewer < operator < admin

  • viewer — Read-only access (GET endpoints)
  • operator — Create/update agents, tasks, skills, use adapters
  • admin — Full access including user management

API key auth grants admin role by default. The key is set via API_KEY env var or the security.api_key DB setting.

Agents can identify themselves with the optional X-Agent-Name header for attribution in audit logs.

Agent Lifecycle

register → heartbeat (5m interval) → fetch assignments → report task status → disconnect

All lifecycle actions go through the adapter protocol (POST /api/adapters).

1. Register
{
  "framework": "generic",
  "action": "register",
  "payload": {
    "agentId": "my-agent-01",
    "name": "My Agent",
    "metadata": { "version": "1.0", "capabilities": ["code", "review"] }
  }
}
2. Heartbeat

Send every ~5 minutes to stay marked as online.

{
  "framework": "generic",
  "action": "heartbeat",
  "payload": {
    "agentId": "my-agent-01",
    "status": "online",
    "metrics": { "tasks_completed": 5, "uptime_seconds": 3600 }
  }
}
3. Fetch Assignments

Returns up to 5 pending tasks sorted by priority (critical → low), then due date.

{
  "framework": "generic",
  "action": "assignments",
  "payload": { "agentId": "my-agent-01" }
}

Response:

{
  "assignments": [
    { "taskId": "42", "description": "Fix login bug\nUsers cannot log in with SSO", "priority": 1 }
  ],
  "framework": "generic"
}
4. Report Task Progress
{
  "framework": "generic",
  "action": "report",
  "payload": {
    "taskId": "42",
    "agentId": "my-agent-01",
    "progress": 75,
    "status": "in_progress",
    "output": "Fixed SSO handler, running tests..."
  }
}

status values: in_progress, done, failed, blocked

5. Disconnect
{
  "framework": "generic",
  "action": "disconnect",
  "payload": { "agentId": "my-agent-01" }
}

Core API Reference

Agents — /api/agents
Method Min Role Description
GET viewer List agents. Query: ?status=online&role=dev&limit=50&offset=0
POST operator Create agent. Body: { name, role, status?, config?, template?, session_key?, soul_content? }
PUT operator Update agent. Body: { name, status?, role?, config?, session_key?, soul_content?, last_activity? }

GET response shape:

{
  "agents": [{
    "id": 1, "name": "scout", "role": "researcher", "status": "online",
    "config": {}, "taskStats": { "total": 10, "assigned": 2, "in_progress": 1, "completed": 7 }
  }],
  "total": 1, "page": 1, "limit": 50
}
Tasks — /api/tasks
Method Min Role Description
GET viewer List tasks. Query: ?status=in_progress&assigned_to=scout&priority=high&project_id=1&limit=50&offset=0
POST operator Create task. Body: { title, description?, status?, priority?, assigned_to?, project_id?, tags?, metadata?, due_date?, estimated_hours? }
PUT operator Bulk status update. Body: { tasks: [{ id, status }] }

Priority values: critical, high, medium, low

Status values: inbox, assigned, in_progress, review, done, failed, blocked, cancelled

Note: Moving a task to done via PUT requires an Aegis quality review approval.

POST response:

{
  "task": {
    "id": 42, "title": "Fix login bug", "status": "assigned",
    "priority": "high", "assigned_to": "scout", "ticket_ref": "GEN-001",
    "tags": ["bug"], "metadata": {}
  }
}
Skills — /api/skills
Method Min Role Description
GET viewer List all skills across roots
GET ?mode=content&source=...&name=... viewer Read a skill's SKILL.md content
GET ?mode=check&source=...&name=... viewer Run security check on a skill
POST operator Create/upsert skill. Body: { source, name, content }
PUT operator Update skill content. Body: { source, name, content }
DELETE ?source=...&name=... operator Delete a skill

Skill sources: user-agents, user-codex, project-agents, project-codex, openclaw

Status — /api/status
Action Min Role Description
GET ?action=overview viewer System status (uptime, memory, disk, sessions)
GET ?action=dashboard viewer Aggregated dashboard data with DB stats
GET ?action=gateway viewer Gateway process status and port check
GET ?action=models viewer Available AI models (catalog + local Ollama)
GET ?action=health viewer Health checks (gateway, disk, memory)
GET ?action=capabilities viewer Feature flags: gateway reachable, Claude home, subscriptions
Adapters — /api/adapters
Method Min Role Description
GET viewer List available framework adapter names
POST operator Execute adapter action (see Agent Lifecycle above)

Framework Adapter Protocol

All agent lifecycle operations use a single endpoint:

POST /api/adapters
Content-Type: application/json
x-api-key: <key>

{
  "framework": "<adapter-name>",
  "action": "<action>",
  "payload": { ... }
}

Available frameworks: generic, openclaw, crewai, langgraph, autogen, claude-sdk

Available actions: register, heartbeat, report, assignments, disconnect

All adapters implement the same FrameworkAdapter interface — choose the one matching your agent framework, or use generic as a universal fallback.

Payload shapes by action:

Action Required Fields Optional Fields
register agentId, name metadata
heartbeat agentId status, metrics
report taskId, agentId progress, status, output
assignments agentId —
disconnect agentId —

Environment Variables

Variable Default Description
API_KEY — API key for agent/script authentication
OPENCLAW_GATEWAY_HOST 127.0.0.1 Gateway host address
OPENCLAW_GATEWAY_PORT 18789 Gateway port
OPENCLAW_STATE_DIR ~/.openclaw OpenClaw state directory
OPENCLAW_CONFIG_PATH <state-dir>/openclaw.json Gateway config file path
MC_CLAUDE_HOME ~/.claude Claude home directory

Real-Time Events

MC broadcasts events via SSE (/api/events) and WebSocket. Key event types:

  • agent.created, agent.updated, agent.status_changed
  • task.created, task.updated, task.status_changed

Subscribe to SSE for live dashboard updates when building integrations.

1---
2name: mission-control
3description: "Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs."
4---
5 
6# Mission Control Agent Skill
7 
8Mission Control (MC) is an AI agent orchestration dashboard with real-time SSE/WebSocket, a skill registry, framework adapters, and RBAC. This skill teaches agents how to interact with MC APIs programmatically.
9 
10## Quick Start
11 
12**Base URL:** `http://localhost:3000` (default Next.js dev) or your deployed host.
13 
14**Auth header:** `x-api-key: <your-api-key>`
15 
16**Register + heartbeat in two calls:**
17 
18```bash
19# 1. Register
20curl -X POST http://localhost:3000/api/adapters \
21 -H "Content-Type: application/json" \
22 -H "x-api-key: $MC_API_KEY" \
23 -d '{
24 "framework": "generic",
25 "action": "register",
26 "payload": { "agentId": "my-agent-01", "name": "My Agent" }
27 }'
28 
29# 2. Heartbeat (repeat every 5 minutes)
30curl -X POST http://localhost:3000/api/adapters \
31 -H "Content-Type: application/json" \
32 -H "x-api-key: $MC_API_KEY" \
33 -d '{
34 "framework": "generic",
35 "action": "heartbeat",
36 "payload": { "agentId": "my-agent-01", "status": "online" }
37 }'
38```
39 
40## Authentication
41 
42MC supports two auth methods:
43 
44| Method | Header | Use Case |
45|--------|--------|----------|
46| API Key | `x-api-key: <key>` or `Authorization: Bearer <key>` | Agents, scripts, CI/CD |
47| Session cookie | `Cookie: __Host-mc-session=<token>` (HTTPS) or `mc-session=<token>` (HTTP) | Browser UI |
48 
49**Roles (hierarchical):** `viewer` < `operator` < `admin`
50 
51- **viewer** — Read-only access (GET endpoints)
52- **operator** — Create/update agents, tasks, skills, use adapters
53- **admin** — Full access including user management
54 
55API key auth grants `admin` role by default. The key is set via `API_KEY` env var or the `security.api_key` DB setting.
56 
57Agents can identify themselves with the optional `X-Agent-Name` header for attribution in audit logs.
58 
59## Agent Lifecycle
60 
61```
62register → heartbeat (5m interval) → fetch assignments → report task status → disconnect
63```
64 
65All lifecycle actions go through the adapter protocol (`POST /api/adapters`).
66 
67### 1. Register
68 
69```json
70{
71 "framework": "generic",
72 "action": "register",
73 "payload": {
74 "agentId": "my-agent-01",
75 "name": "My Agent",
76 "metadata": { "version": "1.0", "capabilities": ["code", "review"] }
77 }
78}
79```
80 
81### 2. Heartbeat
82 
83Send every ~5 minutes to stay marked as online.
84 
85```json
86{
87 "framework": "generic",
88 "action": "heartbeat",
89 "payload": {
90 "agentId": "my-agent-01",
91 "status": "online",
92 "metrics": { "tasks_completed": 5, "uptime_seconds": 3600 }
93 }
94}
95```
96 
97### 3. Fetch Assignments
98 
99Returns up to 5 pending tasks sorted by priority (critical → low), then due date.
100 
101```json
102{
103 "framework": "generic",
104 "action": "assignments",
105 "payload": { "agentId": "my-agent-01" }
106}
107```
108 
109**Response:**
110 
111```json
112{
113 "assignments": [
114 { "taskId": "42", "description": "Fix login bug\nUsers cannot log in with SSO", "priority": 1 }
115 ],
116 "framework": "generic"
117}
118```
119 
120### 4. Report Task Progress
121 
122```json
123{
124 "framework": "generic",
125 "action": "report",
126 "payload": {
127 "taskId": "42",
128 "agentId": "my-agent-01",
129 "progress": 75,
130 "status": "in_progress",
131 "output": "Fixed SSO handler, running tests..."
132 }
133}
134```
135 
136`status` values: `in_progress`, `done`, `failed`, `blocked`
137 
138### 5. Disconnect
139 
140```json
141{
142 "framework": "generic",
143 "action": "disconnect",
144 "payload": { "agentId": "my-agent-01" }
145}
146```
147 
148## Core API Reference
149 
150### Agents — `/api/agents`
151 
152| Method | Min Role | Description |
153|--------|----------|-------------|
154| GET | viewer | List agents. Query: `?status=online&role=dev&limit=50&offset=0` |
155| POST | operator | Create agent. Body: `{ name, role, status?, config?, template?, session_key?, soul_content? }` |
156| PUT | operator | Update agent. Body: `{ name, status?, role?, config?, session_key?, soul_content?, last_activity? }` |
157 
158**GET response shape:**
159 
160```json
161{
162 "agents": [{
163 "id": 1, "name": "scout", "role": "researcher", "status": "online",
164 "config": {}, "taskStats": { "total": 10, "assigned": 2, "in_progress": 1, "completed": 7 }
165 }],
166 "total": 1, "page": 1, "limit": 50
167}
168```
169 
170### Tasks — `/api/tasks`
171 
172| Method | Min Role | Description |
173|--------|----------|-------------|
174| GET | viewer | List tasks. Query: `?status=in_progress&assigned_to=scout&priority=high&project_id=1&limit=50&offset=0` |
175| POST | operator | Create task. Body: `{ title, description?, status?, priority?, assigned_to?, project_id?, tags?, metadata?, due_date?, estimated_hours? }` |
176| PUT | operator | Bulk status update. Body: `{ tasks: [{ id, status }] }` |
177 
178**Priority values:** `critical`, `high`, `medium`, `low`
179 
180**Status values:** `inbox`, `assigned`, `in_progress`, `review`, `done`, `failed`, `blocked`, `cancelled`
181 
182Note: Moving a task to `done` via PUT requires an Aegis quality review approval.
183 
184**POST response:**
185 
186```json
187{
188 "task": {
189 "id": 42, "title": "Fix login bug", "status": "assigned",
190 "priority": "high", "assigned_to": "scout", "ticket_ref": "GEN-001",
191 "tags": ["bug"], "metadata": {}
192 }
193}
194```
195 
196### Skills — `/api/skills`
197 
198| Method | Min Role | Description |
199|--------|----------|-------------|
200| GET | viewer | List all skills across roots |
201| GET `?mode=content&source=...&name=...` | viewer | Read a skill's SKILL.md content |
202| GET `?mode=check&source=...&name=...` | viewer | Run security check on a skill |
203| POST | operator | Create/upsert skill. Body: `{ source, name, content }` |
204| PUT | operator | Update skill content. Body: `{ source, name, content }` |
205| DELETE `?source=...&name=...` | operator | Delete a skill |
206 
207**Skill sources:** `user-agents`, `user-codex`, `project-agents`, `project-codex`, `openclaw`
208 
209### Status — `/api/status`
210 
211| Action | Min Role | Description |
212|--------|----------|-------------|
213| GET `?action=overview` | viewer | System status (uptime, memory, disk, sessions) |
214| GET `?action=dashboard` | viewer | Aggregated dashboard data with DB stats |
215| GET `?action=gateway` | viewer | Gateway process status and port check |
216| GET `?action=models` | viewer | Available AI models (catalog + local Ollama) |
217| GET `?action=health` | viewer | Health checks (gateway, disk, memory) |
218| GET `?action=capabilities` | viewer | Feature flags: gateway reachable, Claude home, subscriptions |
219 
220### Adapters — `/api/adapters`
221 
222| Method | Min Role | Description |
223|--------|----------|-------------|
224| GET | viewer | List available framework adapter names |
225| POST | operator | Execute adapter action (see Agent Lifecycle above) |
226 
227## Framework Adapter Protocol
228 
229All agent lifecycle operations use a single endpoint:
230 
231```
232POST /api/adapters
233Content-Type: application/json
234x-api-key: <key>
235 
236{
237 "framework": "<adapter-name>",
238 "action": "<action>",
239 "payload": { ... }
240}
241```
242 
243**Available frameworks:** `generic`, `openclaw`, `crewai`, `langgraph`, `autogen`, `claude-sdk`
244 
245**Available actions:** `register`, `heartbeat`, `report`, `assignments`, `disconnect`
246 
247All adapters implement the same `FrameworkAdapter` interface — choose the one matching your agent framework, or use `generic` as a universal fallback.
248 
249**Payload shapes by action:**
250 
251| Action | Required Fields | Optional Fields |
252|--------|----------------|-----------------|
253| `register` | `agentId`, `name` | `metadata` |
254| `heartbeat` | `agentId` | `status`, `metrics` |
255| `report` | `taskId`, `agentId` | `progress`, `status`, `output` |
256| `assignments` | `agentId` | — |
257| `disconnect` | `agentId` | — |
258 
259## Environment Variables
260 
261| Variable | Default | Description |
262|----------|---------|-------------|
263| `API_KEY` | — | API key for agent/script authentication |
264| `OPENCLAW_GATEWAY_HOST` | `127.0.0.1` | Gateway host address |
265| `OPENCLAW_GATEWAY_PORT` | `18789` | Gateway port |
266| `OPENCLAW_STATE_DIR` | `~/.openclaw` | OpenClaw state directory |
267| `OPENCLAW_CONFIG_PATH` | `<state-dir>/openclaw.json` | Gateway config file path |
268| `MC_CLAUDE_HOME` | `~/.claude` | Claude home directory |
269 
270## Real-Time Events
271 
272MC broadcasts events via SSE (`/api/events`) and WebSocket. Key event types:
273 
274- `agent.created`, `agent.updated`, `agent.status_changed`
275- `task.created`, `task.updated`, `task.status_changed`
276 
277Subscribe to SSE for live dashboard updates when building integrations.
278 
View all files on GitHub →

Details

License
MIT
Stars on the repo
★ 6,320
Checked
Source
builderz-labs/mission-control ↗
Creator
builderz-labs · 1 listing
View creator

Made with mission-control

Mission Control Agent Skill — Mission Control operator field notes (from the builderz-labs/mission-control README)
Mission Control Agent Skill — Mission Control operator field notes (from the builderz-labs/mission-control README)

by builderz-labs

Mission Control Agent Skill — Mission Control task board with assigned, in-progress, and review columns of agent tasks (from the builderz-labs/mission-control README)
Mission Control Agent Skill — Mission Control task board with assigned, in-progress, and review columns of agent tasks (from the builderz-labs/mission-control README)

by builderz-labs

Mission Control Agent Skill — Mission Control agents panel showing a five-agent squad with roles, heartbeats, and workspace conventions (from the builderz-labs/mission-control README)
Mission Control Agent Skill — Mission Control agents panel showing a five-agent squad with roles, heartbeats, and workspace conventions (from the builderz-labs/mission-control README)

by builderz-labs

Similar skills

See all →
Browser Testing Suiteaddyosmani/agent-skills · by addyosmaniTests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.★ 98.7k GitHub starsEverything MCPmodelcontextprotocol/servers · by modelcontextprotocolThis MCP server attempts to exercise all the features of the MCP protocol. It is not intended to be a useful server, but rather a test…★ 90.5k GitHub starsWeb Content Fetchermodelcontextprotocol/servers · by modelcontextprotocolA Model Context Protocol server that provides web content fetching capabilities. This server enables LLMs to retrieve and process content…★ 90.5k GitHub starsFilesystem Operationsmodelcontextprotocol/servers · by modelcontextprotocolNode.js server implementing Model Context Protocol (MCP) for filesystem operations.★ 90.5k GitHub starsLibrary Reference Toolupstash/context7 · by upstashThis skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.★ 62.3k GitHub starsChrome DevTools DebuggerChromeDevTools/chrome-devtools-mcp · by ChromeDevToolsUses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).★ 52.4k GitHub stars