← 返回 Skills 市场
reed1898

Agent Dashboard Sync

作者 Reed · GitHub ↗ · v0.1.0
cross-platform ⚠ suspicious
273
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-dashboard-sync
功能描述
Sync OpenClaw fleet runtime/heartbeat/cron status to Cloudflare KV and serve dashboard-ready data via Worker API. Use when setting up or operating the Agent...
使用说明 (SKILL.md)

Agent Dashboard Sync

Operate dashboard data sync as a no-LLM pipeline.

Hard Rules

  1. Keep high-frequency state out of Git commits.
  2. Use Cloudflare Worker + KV for runtime sync.
  3. Run collector from local cron (*/2 * * * *) and do not call LLM in collector path.
  4. Never commit or print production tokens/secrets in files, logs, or screenshots.
  5. Do not publish absolute paths in skill docs; use relative paths or placeholders (\x3CPROJECTS_ROOT>, \x3CSHARED_ROOT>).

Scope Boundary

  • This skill owns: collector, Worker ingest/read API, KV schema, cron deployment, dashboard data source wiring.
  • This skill does not own: cross-agent protocol, constitution governance, Discord routing rules.

KV Data Contract (v1)

  • fleet:registry
  • fleet:heartbeat:\x3Cagent_id>
  • fleet:cron:\x3Cagent_id>
  • fleet:runtime:\x3Cagent_id>
  • fleet:events:recent
  • fleet:updated_at

See references/schema.md for payload shape.

Minimal Rollout

  1. Deploy Worker + KV namespace.
  2. Configure dashboard env to cloudflare mode.
  3. Install collector cron on each node with unique AGENT_ID.
  4. Verify /health, then /fleet, then dashboard UI.

Security Checklist

  • Store INGEST_TOKEN and READ_TOKEN as worker secrets.
  • Keep dashboard read token server-side (DASHBOARD_READ_TOKEN), never client-exposed.
  • Keep NEXT_PUBLIC_* vars non-sensitive only.
  • Redact tokens before sharing commands/logs.

Runbook Links

  • Worker setup and command sequence: references/worker-setup.md
  • Collector and crontab setup: references/collector-cron.md
  • Env variable matrix: references/env-matrix.md
  • Data schema reference: references/schema.md
  • Security policy for all agents: references/security-rules.md
安全使用建议
This skill conceptually fits its description, but you should not install or deploy it without doing the following first: - Obtain and review the collector code (collectors/openclaw-state-collector) that the cron runs. Confirm it only collects the minimal telemetry described and does not read or send files, shell history, chat content, or credentials. - Ensure the Worker is deployed to an account you control; verify the wrangler.json bindings and that KV namespace IDs map to your resources. - Create least-privilege tokens for INGEST_TOKEN/READ_TOKEN and verify Worker enforces Bearer auth, rate limits, and schema validation as documented. - Add automated secret scans to your CI and verify example snippets use placeholders (they do in these docs). Rotate secrets if anything is exposed. - Test in an isolated staging environment (with synthetic agent IDs) to confirm payload contents, ring-buffer size, and that no PII or command outputs are transmitted. Because the runtime behaviour of the collector is not included here, you should treat this skill as untrusted until you can audit the collector implementation. If you cannot review that code, do not deploy in production.
功能分析
Type: OpenClaw Skill Name: agent-dashboard-sync Version: 0.1.0 The agent-dashboard-sync skill is a legitimate administrative tool designed to synchronize agent fleet telemetry (heartbeats, cron status, and runtime metadata) to a Cloudflare KV store for dashboard visualization. The bundle includes comprehensive security guidelines in references/security-rules.md, emphasizing secret hygiene, data minimization, and secure transport. All high-risk operations, such as network requests to Cloudflare Workers and local cron job scheduling (references/collector-cron.md), are well-documented and directly support the stated purpose without evidence of malicious intent or unauthorized data exfiltration.
能力评估
Purpose & Capability
The name/description (sync fleet runtime/heartbeat/cron to Cloudflare KV and provide a Worker API) align with the instructions (deploy Worker, create KV, set secrets, run a collector via cron that POSTs to a Worker endpoint). However the skill metadata declares no required env vars/credentials while the runtime docs clearly require several tokens (INGEST_TOKEN, READ_TOKEN, REPORT_TOKEN, DASHBOARD_READ_TOKEN) and AGENT_ID on nodes — a transparency mismatch.
Instruction Scope
SKILL.md + references specify running a node-side collector via an npm script (collectors/openclaw-state-collector collect) on a cron schedule and posting telemetry to a Worker. The repository does not include the collector code here, so there is no way to verify the collector only sends the minimal telemetry described. The docs forbid LLM calls and PII/secret leakage, but those are policy statements you must verify by reviewing the actual collector implementation before trusting it in production.
Install Mechanism
Instruction-only skill with no install spec and no downloaded artifacts. This minimizes installation-side risk; nothing will be written or executed by the platform beyond following the textual operational steps. The higher risk is absent code to audit outside the skill bundle.
Credentials
The required secrets (INGEST_TOKEN, READ_TOKEN, REPORT_TOKEN, DASHBOARD_READ_TOKEN) and AGENT_ID are appropriate for the stated Cloudflare Worker + collector architecture. But the skill metadata lists no required env vars or primary credential — the docs expect secrets and per-node envs that should have been declared. Lack of declared required env vars reduces visibility and increases the chance of accidental misconfiguration or secret misuse.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent platform privileges or claim to modify other skills or global agent settings. No autonomously forced inclusion is present.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install agent-dashboard-sync
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /agent-dashboard-sync 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.0
Initial public release: Cloudflare KV + Worker API sync pipeline, collector cron guidance, and publish security rules.
元数据
Slug agent-dashboard-sync
版本 0.1.0
许可证
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Agent Dashboard Sync 是什么?

Sync OpenClaw fleet runtime/heartbeat/cron status to Cloudflare KV and serve dashboard-ready data via Worker API. Use when setting up or operating the Agent... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 273 次。

如何安装 Agent Dashboard Sync?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-dashboard-sync」即可一键安装,无需额外配置。

Agent Dashboard Sync 是免费的吗?

是的,Agent Dashboard Sync 完全免费(开源免费),可自由下载、安装和使用。

Agent Dashboard Sync 支持哪些平台?

Agent Dashboard Sync 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Agent Dashboard Sync?

由 Reed(@reed1898)开发并维护,当前版本 v0.1.0。

💬 留言讨论