免费在 GitHub 公开

mission-control

Connect AI agents to Mission Control through its API to register agents, retrieve assigned tasks, report progress, manage skills, and check agent or system status from scripts and automated workflows.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

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

builderz-labs/mission-control

查看安装方法

适用场景

Registering agents and reporting their online status
Retrieving assigned tasks and reporting progress
Reading and updating registered skills
Checking agent activity and system health

包含的文件（200）

SKILL.md8.2 KB
.dockerignore231 B
.env.example11.1 KB
.env.test191 B
.github/CODEOWNERS76 B
.github/dependabot.yml1.4 KB
.github/FUNDING.yml31 B
.github/ISSUE_TEMPLATE/bug_report.yml1.9 KB
.github/ISSUE_TEMPLATE/config.yml261 B
.github/ISSUE_TEMPLATE/feature_request.yml2.3 KB
.github/pull_request_template.md825 B
.github/workflows/codeql.yml951 B
.github/workflows/config-integrity.yml2.5 KB
.github/workflows/docker-publish.yml2.4 KB
.github/workflows/osv-scanner.yml557 B
.github/workflows/quality-gate.yml1.8 KB
.github/workflows/scorecard.yml1.2 KB
.github/workflows/screenshot-drift.yml3.9 KB
.github/workflows/star-chart.yml1.1 KB
.gitignore695 B
.node-version3 B
.npmrc48 B
.nvmrc3 B
CHANGELOG.md20.3 KB
CLAUDE.md3.3 KB
CODE_OF_CONDUCT.md5.4 KB
CONTRIBUTING.md2.1 KB
docker-compose.hardened.yml486 B
docker-compose.yml3.0 KB
docker-entrypoint.sh1.3 KB
Dockerfile4.6 KB
docs/agent-setup.md9.9 KB
docs/cli-agent-control.md4.2 KB
docs/cli-integration.md3.3 KB
docs/deployment.md23.7 KB
docs/mission-control-activity.png45.6 KB
docs/mission-control-agents.png59.6 KB
docs/mission-control-cron.png62.3 KB
docs/mission-control-memory.png37.5 KB
docs/mission-control-overview.png44.8 KB
docs/mission-control-tasks.png85.9 KB
docs/openclaw-config-compatibility.md1.4 KB
docs/operator-field-notes.webp74.5 KB
docs/orchestration.md10.5 KB
docs/plans/2026-03-10-onboarding-walkthrough-hardening.md1.1 KB
docs/plans/2026-03-20-mission-control-platform-cli-tui-prd.md8.4 KB
docs/quickstart.md7.6 KB
docs/releases/2.0.0.md10.0 KB
docs/releases/2.0.1.md4.6 KB
docs/releases/2.2.0.md2.5 KB
docs/releases/2.3.0.md2.8 KB
docs/SCREENSHOT-GUIDE.md2.9 KB
docs/SECURITY-HARDENING.md12.7 KB
docs/star-history-dark.svg5.5 KB
docs/star-history-light.svg5.5 KB
eslint.config.mjs1.4 KB
examples/MULTI-PROVIDER-DEMO.md38.4 KB
install.ps116.1 KB
install.sh15.7 KB
LICENSE1.0 KB
messages/ar.json108.2 KB
messages/de.json91.6 KB
messages/en.json83.2 KB
messages/es.json92.2 KB
messages/fr.json94.8 KB
messages/ja.json102.0 KB
messages/ko.json92.7 KB
messages/pt.json91.7 KB
messages/ru.json122.0 KB
messages/zh-tw.json82.3 KB
messages/zh.json82.0 KB
next.config.js2.4 KB
openapi.json330.6 KB
openclaw_hardening_guide.md6.9 KB
ops/mc-provisioner-daemon.js11.6 KB
ops/provisioner-limits.cjs907 B
ops/templates/openclaw-gateway@.service567 B
package.json4.2 KB
playwright.config.ts1.3 KB
playwright.openclaw.gateway.config.ts627 B
playwright.openclaw.local.config.ts625 B
pnpm-lock.yaml328.7 KB
pnpm-workspace.yaml743 B
postcss.config.js71 B
public/brand/claude-logo.png61.4 KB
public/brand/codex-logo.png2.8 KB
public/brand/hermes-logo.png24.8 KB
public/brand/mc-logo-128.png16.7 KB
public/brand/mc-logo-256.png63.0 KB
public/brand/mc-logo-512.png279.3 KB
public/brand/openclaw-logo.png25.1 KB
public/llms.txt1.3 KB
public/mc-logo.png1.8 MB
public/mc.png2.3 MB
public/office-sprites/cc0-hero/ATTRIBUTION-CC0-HERO.txt210 B
public/office-sprites/cc0-hero/player_full_animation.png49.4 KB
public/office-sprites/cc0-hero/player.png13.6 KB
public/office-sprites/desk.svg665 B
public/office-sprites/floor-tile.svg436 B
public/office-sprites/kenney/ATTRIBUTION-KENNEY.txt575 B
public/office-sprites/kenney/chairDesk.png997 B
public/office-sprites/kenney/computerScreen.png353 B
public/office-sprites/kenney/desk.png560 B
public/office-sprites/kenney/floorFull.png795 B
public/office-sprites/kenney/plantSmall1.png257 B
public/office-sprites/kenney/plantSmall2.png248 B
public/office-sprites/kenney/rugRectangle.png418 B
public/office-sprites/kenney/tableCross.png512 B
public/office-sprites/lounge-rug.svg358 B
public/office-sprites/plant.svg487 B
public/office-sprites/worker-base.svg603 B
public/office-sprites/worker-idle-a.svg603 B
public/office-sprites/worker-idle-b.svg603 B
public/office-sprites/worker-type-a.svg601 B
public/office-sprites/worker-type-b.svg601 B
public/office-sprites/worker-walk-a.svg603 B
public/office-sprites/worker-walk-b.svg603 B
public/robots.txt198 B
README.md11.9 KB
RELEASE.md1.6 KB
scripts/agent-heartbeat.sh7.1 KB
scripts/api-contract-parity.ignore670 B
scripts/check-api-contract-parity.mjs5.1 KB
scripts/check-node-version.mjs681 B
scripts/check-standalone-artifact.mjs2.4 KB
scripts/check-workflow-action-pins.py1.3 KB
scripts/deploy-standalone.sh6.2 KB
scripts/e2e-openclaw/bin/clawdbot353 B
scripts/e2e-openclaw/bin/openclaw353 B
scripts/e2e-openclaw/bin/opencode699 B
scripts/e2e-openclaw/mock-gateway.mjs1.5 KB
scripts/e2e-openclaw/start-e2e-server.mjs8.4 KB
scripts/gen-star-history.py5.8 KB
scripts/generate-env.sh2.4 KB
scripts/load-env.sh2.1 KB
scripts/load-env.test.sh1.9 KB
scripts/mc-base-url.cjs1.0 KB
scripts/mc-cli.cjs25.4 KB
scripts/mc-mcp-server.cjs30.1 KB
scripts/mc-server.cjs2.8 KB
scripts/mc-tui.cjs45.9 KB
scripts/notification-daemon.sh10.1 KB
scripts/prepare-standalone-artifact.mjs1.8 KB
scripts/security-audit.sh6.5 KB
scripts/security-audit.test.sh1.4 KB
scripts/smoke-staging.mjs5.3 KB
scripts/start-standalone.sh1.5 KB
scripts/station-doctor.sh6.7 KB
scripts/take-screenshots.ts3.2 KB
SECURITY.md2.5 KB
skills/mission-control-installer/README.md1.7 KB
skills/mission-control-installer/skill.json786 B
skills/mission-control-manage/README.md2.6 KB
skills/mission-control-manage/skill.json605 B
src/app/[[...panel]]/page.tsx26.8 KB
src/app/api/activities/route.ts7.7 KB
src/app/api/adapters/route.ts4.3 KB
src/app/api/agent-runtimes/route.ts3.9 KB
src/app/api/agents/[id]/attribution/route.ts12.1 KB
src/app/api/agents/[id]/diagnostics/route.ts14.2 KB
src/app/api/agents/[id]/files/route.ts6.3 KB
src/app/api/agents/[id]/heartbeat/route.ts8.9 KB
src/app/api/agents/[id]/hide/route.ts2.6 KB
src/app/api/agents/[id]/keys/route.ts7.1 KB
src/app/api/agents/[id]/memory/route.ts11.2 KB
src/app/api/agents/[id]/route.ts11.0 KB
src/app/api/agents/[id]/soul/route.ts11.0 KB
src/app/api/agents/[id]/wake/route.ts2.1 KB
src/app/api/agents/comms/route.ts5.8 KB
src/app/api/agents/evals/route.ts5.7 KB
src/app/api/agents/message/route.ts3.3 KB
src/app/api/agents/optimize/route.ts3.6 KB
src/app/api/agents/register/route.ts4.7 KB
src/app/api/agents/route.ts17.0 KB
src/app/api/agents/sync/route.ts2.3 KB
src/app/api/alerts/route.ts12.9 KB
src/app/api/audit/route.ts1.9 KB
src/app/api/auth/access-requests/route.ts5.4 KB
src/app/api/auth/google/disconnect/route.ts1.4 KB
src/app/api/auth/google/route.ts4.4 KB
src/app/api/auth/login/route.ts2.6 KB
src/app/api/auth/logout/route.test.ts2.0 KB
src/app/api/auth/logout/route.ts1.3 KB
src/app/api/auth/me/route.ts5.1 KB
src/app/api/auth/users/route.ts7.1 KB
src/app/api/backup/route.ts6.4 KB
src/app/api/channels/route.ts9.9 KB
src/app/api/chat/conversations/route.ts3.6 KB
src/app/api/chat/messages/[id]/route.ts2.6 KB
src/app/api/chat/messages/route.ts26.9 KB
src/app/api/chat/session-prefs/route.ts4.0 KB
src/app/api/claude-tasks/route.ts907 B
src/app/api/claude/sessions/route.ts3.8 KB
src/app/api/cleanup/route.ts7.2 KB
src/app/api/connect/route.ts6.1 KB
src/app/api/cron/route.ts14.6 KB
src/app/api/debug/route.ts5.8 KB
src/app/api/diagnostics/route.ts6.7 KB
src/app/api/docs/content/route.ts1.4 KB
src/app/api/docs/route.ts464 B

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

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.

评价

还没有评价。欢迎分享你的使用感受。

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

报告此技能的问题

安装

用命令安装

npx skills add https://github.com/builderz-labs/mission-control --skill mission-control

粘贴到终端中运行（需要 Node.js）。可以选择安装到 Claude Code、Codex 等代理。

让代理安装

请安装以下 Agent Skill。
https://github.com/builderz-labs/mission-control

请先检查 SKILL.md 和附带文件的内容，确认没有可疑的处理（向外部发送数据、读取认证信息等）后，再放到 ~/.claude/skills/mission-control/（Claude Code）或 ~/.agents/skills/mission-control/（Codex）。

把这段文字直接发给 Claude Code 或 Codex，它会先检查内容再安装。

在 GitHub 查看源代码

仓库: builderz-labs/mission-control
星标: 6,374
复刻: 145
分类: 效率提升
许可证: MIT
原文语言: 英语
最后更新: 2026年10月19日

技能是给 AI 代理的指令和脚本的集合。cccskills 不保证其内容的安全性，安装前请务必确认内容。