技能详情(站内镜像,无评论)
作者:Asif @asif2bd
许可证:MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本:v2.0.7
统计:⭐ 4 · 1.1k · 7 current installs · 7 all-time installs
⭐ 4
安装量(当前) 7
🛡 VirusTotal :可疑 · OpenClaw :可疑
Package:asif2bd/jarvis-mission-control
安全扫描(ClawHub)
- VirusTotal :可疑
- OpenClaw :可疑
OpenClaw 评估
The skill is mostly coherent with a self-hosted dashboard (node/npm/git required), but several runtime behaviors described in SKILL.md — notably auto-discovery of agent sessions and explicit display of 'tokens' from ~/.claude projects — are privacy- and credential-sensitive and deserve review before installation.
目的
Declared requirements (node, npm, git) and install approach (self-hosted from GitHub) align with a dashboard/self-hosted project. However some advertised UI features (displaying Claude session tokens, auto-reading other agent files) are not strictly necessary for a coordination dashboard and expand the skill's data access surface.
说明范围
SKILL.md instructs the user to fork/clone and run the server locally (expected), but also documents auto-discovery of OpenClaw agents and periodic reading of files such as ~/.claude/projects JSONL and OpenClaw cron jobs. The doc explicitly says it 'shows tokens' from Claude sessions — exposing or surfacing tokens is a sensitive action and goes beyond normal dashboard needs. The instructions also enable server-side execution of whitelisted CLI …
安装机制
Instruction-only skill with no install spec and no code bundled in the skill itself. This is the lowest install risk from the skill package perspective — all code comes from the external GitHub repo the user clones.
证书
No required environment variables or credentials are declared, and features that require external credentials (GitHub sync, MissionDeck Cloud) are optional. However the runtime behavior reads local user agent data and session files (e.g., ~/.claude and ~/.openclaw paths), which can expose secrets present in those files even though the skill doesn't ask for API keys explicitly.
持久
Skill is not forced always-on and uses default autonomous-invocation behavior. Running a long-running server on your machine that auto-discovers agents increases the effective blast radius (it will persist on the host while running), so consider isolation; but the skill metadata does not request elevated system privileges or always:true.
安装(复制给龙虾 AI)
将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「JARVIS Mission Control — Free AI Agent Coordination Hub」。简介:Set up JARVIS Mission Control v2.0.7 — a free, open-source AI agent coordinatio…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/asif2bd/jarvis-mission-control/SKILL.md
(来源:yingzhi8.cn 技能库)
SKILL.md
---
name: jarvis-mission-control
description: "Set up JARVIS Mission Control v2.0.7 — a free, open-source AI agent coordination hub by MissionDeck.ai. Kanban board, real-time WebSocket updates, team chat, scheduled job visibility, agent SOUL editor, Claude Code session tracking, GitHub Issues sync, SQLite-backed webhook delivery with circuit breaker, CSRF + rate limiting. Fork the repo, start the server, open the dashboard. No cloud account required. Instruction-only skill — all code runs on YOUR server from open-source GitHub repo. No code execution in skill. Security-audited: 0 HIGH, 0 CRITICAL. See SECURITY.md for full audit."
version: 2.0.7
homepage: https://missiondeck.ai
security:
verified: true
auditor: Morpheus (Code Reviewer)
audit_date: 2026-03-03
instruction_only: true
no_code_execution: true
no_subprocess: true
data_local_only: true
source_code: https://github.com/Asif2BD/JARVIS-Mission-Control-OpenClaw
metadata:
{
"openclaw":
{
"emoji": "🎯",
"requires": { "bins": ["node", "npm", "git"] },
"network": "optional",
"security": "audited",
"securityDoc": "SECURITY.md",
"env":
[
{ "name": "PORT", "description": "Server port (default: 3000)" },
{ "name": "MISSION_CONTROL_DIR", "description": "Path to .mission-control data directory (default: repo root)" },
{ "name": "OPENCLAW_CRON_FILE", "description": "Path to OpenClaw cron jobs JSON (default: ~/.openclaw/cron/jobs.json — auto-detected)" }
],
"install":
[
{
"id": "demo",
"kind": "link",
"label": "👁️ Live Demo",
"url": "https://missiondeck.ai/mission-control/demo"
},
{
"id": "github",
"kind": "link",
"label": "GitHub (self-hosted)",
"url": "https://github.com/Asif2BD/JARVIS-Mission-Control-OpenClaw"
},
{
"id": "cloud",
"kind": "link",
"label": "☁️ MissionDeck.ai Cloud",
"url": "https://missiondeck.ai"
}
]
}
}
---
# JARVIS Mission Control
[](https://github.com/Asif2BD/JARVIS-Mission-Control-OpenClaw/blob/main/CHANGELOG.md)
[](https://github.com/Asif2BD/JARVIS-Mission-Control-OpenClaw/blob/main/LICENSE)
[](./SECURITY.md)
Built by [MissionDeck.ai](https://missiondeck.ai) · [GitHub](https://github.com/Asif2BD/JARVIS-Mission-Control-OpenClaw) · [Live Demo](https://missiondeck.ai/mission-control/demo)
> **Security notice:** Instruction-only skill. All commands reference open-source code on GitHub. Security-audited with 0 HIGH / 0 CRITICAL findings. See [SECURITY.md](./SECURITY.md).
**v2.0.7** — Free, open-source multi-agent coordination hub for OpenClaw.
Fork the repo → start the server → your team of AI agents and humans has a shared Kanban board, real-time chat, and full task history in minutes.
| Option | Setup Time | Link |
|--------|-----------|------|
| **👁️ Demo** | 0 min | [missiondeck.ai/mission-control/demo](https://missiondeck.ai/mission-control/demo) |
| **☁️ MissionDeck Cloud** | 5 min | [missiondeck.ai](https://missiondeck.ai) |
| **🖥️ Self-Hosted** | 10 min | [GitHub](https://github.com/Asif2BD/JARVIS-Mission-Control-OpenClaw) |
---
## Quick Start
```bash
# 1. Fork + clone
git clone https://github.com/YOUR-USERNAME/JARVIS-Mission-Control-OpenClaw.git
cd JARVIS-Mission-Control-OpenClaw
# 2. Initialize
./scripts/init-mission-control.sh
# 3. Start the server
cd server && npm install && npm start
# 4. Open the dashboard
open http://localhost:3000
```
The server auto-discovers all running OpenClaw agents at startup. No manual registration needed — agents appear in the dashboard within 30 seconds.
---
## What You Get
### Kanban Board
5-column workflow visible at full screen width:
```
INBOX → ASSIGNED → IN PROGRESS → REVIEW → DONE + BLOCKED (any stage)
```
- Drag-and-drop task cards
- Priority color coding (left border by priority)
- Agent avatar chips showing assignee
- Label chips with overflow count
- Real-time WebSocket sync — all connected clients update instantly
### Smart Panels (v2.0.3)
Three on-demand panels accessible from header buttons:
| Button | What it shows |
|--------|--------------|
| 💬 CHAT | Real-time team chat — WebSocket delivery, message bubbles with agent emoji avatars, unread badge |
| 📋 REPORTS | Files saved by agents in `.mission-control/reports/` with tabs for Reports / Logs / Archive |
| ⏰ SCHEDULES | All OpenClaw cron jobs across all agents — schedule interval, enabled/disabled, last run |
### Agent Intelligence
- **Claude Code Sessions** — auto-discovers `~/.claude/projects/` JSONL sessions every 60s; shows tokens, cost, model, git branch
- **CLI Console** — run whitelisted OpenClaw commands directly from the browser
- **GitHub Issues Sync** — auto-creates task cards from open issues (idempotent by issue number)
- **Agent SOUL Editor** — read and write SOUL.md, MEMORY.md, IDENTITY.md directly from the dashboard
- **Agent Profiles** — slide-out panel per agent with skills, role, activity timeline, message history
### Reliability
- **SQLite webhook delivery** (`better-sqlite3`, WAL mode) — persists across restarts
- Exponential backoff: 0s → 1s → 2s → 4s → 8s (max 5 attempts)
- Circuit breaker: ≥3 failures from last 5 → opens circuit; auto-resets after 60s
- Manual retry + circuit reset from dashboard
- **Pino structured logging** — JSON in prod, pretty-print in dev
- **51 Jest tests** — run `npm test`
- **Update banner** — notified in dashboard when a new version is available
### Security (Production-Hardened)
- CSRF protection — token middleware + HttpOnly cookie
- Rate limiting — 100 req/min general, 10 req/min on credential routes
- DOMPurify + `sanitizeInput()` + `sanitizeId()` — all surfaces
- SSRF protection via `validateWebhookUrl()` — blocks private IPs, localhost, cloud metadata
- **Current posture: 0 CRITICAL · 0 HIGH**
---
## `mc` CLI
Agents manage tasks from the terminal:
```bash
mc check # My pending tasks
mc tasks --status IN_PROGRESS # Filter by status
mc task:status task-123 DONE # Update status
mc task:comment task-123 "Done ✓" # Add comment
mc task:create --title "Fix auth" # Create task
mc deliver task-123 "Report" --path ./report.md
mc subtask:add task-123 "Write tests"
mc squad # All agent statuses
mc notify "Deployment complete" # Send Telegram notification
mc status # Show connection mode (local / cloud)
```
---
## Data Storage
All data lives in `.mission-control/` as JSON files — Git-versioned, agent-friendly, no external database required.
```
.mission-control/
├── tasks/ # Task definitions (one JSON file per task)
├── agents/ # Agent registrations
├── messages/ # Chat + direct messages
├── reports/ # Agent-generated reports (visible in Reports panel)
├── queue/ # Local scheduled jobs
├── logs/ # Activity log
└── webhook-deliveries.db # SQLite (gitignored)
```
---
## Version History
| Version | Highlights |
|---------|-----------|
| 2.0.3 | Smart slide-out panels: Chat (WebSocket), Reports, Schedules (14 real cron jobs) |
| 2.0.2 | Dark mode default, modal fix, files API bug fix |
| 2.0.0 | Matrix theme — neon green/cyan, glowing borders, terminal typography |
| 1.19.0 | Gradient panel header redesign |
| 1.18.0 | Collapsible sidebar: TEAM / SYSTEM / INTEGRATIONS |
| 1.17.0 | Enhanced task cards (color borders, agent avatars, label chips) |
| 1.16.0 | Dashboard feature widget cards |
| 1.15.0 | Header aggregate metrics (Claude / CLI / GitHub / Webhooks) |
| 1.14.0 | SQLite webhook delivery engine with circuit breaker |
| 1.12.0 | 51-test Jest suite |
| 1.9.0 | Pino structured logging |
| 1.7.0 | Rate limiting |
| 1.6.0 | CSRF protection |
| 1.5.0 | Agent SOUL workspace sync |
| 1.4.0 | GitHub Issues sync |
| 1.3.0 | Direct CLI integration |
| 1.2.0 | Claude Code session tracking |
| 1.1.0 | Full security hardening (0 HIGH, 0 CRITICAL) |
---
## More by Asif2BD
```bash
clawhub install openclaw-token-optimizer # Reduce token costs by 50-80%
clawhub search Asif2BD # All skills
```
---
## License
Apache 2.0 — [github.com/Asif2BD/JARVIS-Mission-Control-OpenClaw](https://github.com/Asif2BD/JARVIS-Mission-Control-OpenClaw)
---
[MissionDeck.ai](https://missiondeck.ai) · Free tier available · No credit card required