一键导入
register-on-dashclaw
Register any agent (including this one) as a governed agent on a DashClaw instance
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Register any agent (including this one) as a governed agent on a DashClaw instance
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
The single command that gets a DashClaw change ON MAIN AND LIVE — it resolves everything blocking production, never defers, and never hands back a checklist. Lands feature branches on main (rebase, gate, merge, push so Vercel deploys), bumps the unified platform+SDK version, and realigns every *description* of the system with the live code: README, PROJECT_DETAILS, SDK READMEs, /docs, generated artifacts (API inventory, OpenAPI, download bundles), plugins/skills/hooks/MCP, marketing/landing pages, the drift-prone hardcoded counts (routes, SDK methods, MCP tools/resources, guard policies) and stale freshness date-stamps. The one step it can't finish itself is the credential-gated SDK publish (`npm run release:sdks`). Use whenever the user wants to ship, land, or finish a change — get it on main, make it live, cut a release, bump the version, refresh all the docs, make everything accurate, fix wrong counts or old dates. Not for building or debugging the feature itself.
Governance behavior for AI agents governed by DashClaw. Teaches the governance protocol: when to call guard (risk thresholds), how to interpret decisions (allow/warn/block/require_approval), when to record actions, how to wait for approvals, and session lifecycle management. Loads org-specific policies and capabilities from MCP resources at session start. Use with @dashclaw/mcp-server. Trigger on: governed agent, dashclaw governance, guard policy, approval wait, governed capability, risk threshold, action recording, session lifecycle.
Human-in-the-loop approval workflows for governed agent actions
Governance behavior for AI agents governed by DashClaw. Teaches the governance protocol: when to call guard (risk thresholds), how to interpret decisions (allow/warn/block/require_approval), when to record actions, how to wait for approvals, and session lifecycle management. Loads org-specific policies and capabilities from MCP resources at session start. Use with @dashclaw/mcp-server. Trigger on: governed agent, dashclaw governance, guard policy, approval wait, governed capability, risk threshold, action recording, session lifecycle.
Set up a DashClaw instance, install the CLI tool, and configure Claude Code hooks
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"
| name | register-on-dashclaw |
| description | Register any agent (including this one) as a governed agent on a DashClaw instance |
| license | MIT |
| metadata | {"author":"ucsandman","version":"1.0.0","category":"meta"} |
Register any AI agent as a governed entity on a DashClaw instance. This includes the meta act of registering this very agent on DashClaw.
curl -X POST "$DASHCLAW_BASE_URL/api/agents" \
-H "x-api-key: $DASHCLAW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"agent_id": "my-agent",
"agent_name": "My Agent",
"description": "What this agent does",
"capabilities": ["deploy", "api_call", "file_write"]
}'
import { DashClaw } from 'dashclaw';
const claw = new DashClaw({
baseUrl: process.env.DASHCLAW_BASE_URL,
apiKey: process.env.DASHCLAW_API_KEY,
agentId: 'my-agent'
});
// Agent is auto-registered on first guard call or action creation
// Explicit registration is optional but recommended for metadata
Heartbeats let DashClaw know your agent is alive. Missing heartbeats trigger the "Agent Silent" signal (>10 min).
// Single heartbeat
await claw.heartbeat({ status: 'online', metadata: { version: '1.0.0' } });
// Auto-heartbeat (v1 SDK)
import { DashClaw } from 'dashclaw/legacy';
const claw = new DashClaw({ baseUrl, apiKey, agentId: 'my-agent' });
claw.startHeartbeat({ interval: 60000 }); // Every 60 seconds
// Stop when shutting down
claw.stopHeartbeat();
# Python
claw.heartbeat(status="online", metadata={"version": "1.0.0"})
Scope guard policies to a specific agent:
curl -X POST "$DASHCLAW_BASE_URL/api/policies" \
-H "x-api-key: $DASHCLAW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "my-agent-deploy-gate",
"agent_id": "my-agent",
"type": "approval_gate",
"mode": "enforce",
"conditions": {
"action_types": ["deploy"],
"risk_score_min": 50
},
"action": "require_approval",
"reason": "All deploys by my-agent require approval"
}'
For production, register your agent's public key for action signing:
// V1 SDK — register identity
import { DashClaw } from 'dashclaw/legacy';
const claw = new DashClaw({ baseUrl, apiKey, agentId: 'my-agent' });
await claw.registerIdentity({
publicKeyPem: myPublicKey,
algorithm: 'Ed25519',
agentName: 'My Agent'
});
// Revoke an identity when agent is decommissioned
await claw.revokeIdentity('my-agent');
Signature enforcement is runtime-toggleable from /settings?tab=identity. When enabled, all actions must be signed with the registered key.
If the DashClaw instance has DASHCLAW_CLOSED_ENROLLMENT=true, agents must be pre-registered before they can call guard or create actions. Register first, then instrument.
This agent — dashclaw-agent — can be registered on DashClaw as a governed agent. Here's how:
export DASHCLAW_BASE_URL=http://localhost:3000
export DASHCLAW_API_KEY=your-api-key
export DASHCLAW_AGENT_ID=dashclaw-agent
curl -X POST "$DASHCLAW_BASE_URL/api/agents" \
-H "x-api-key: $DASHCLAW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"agent_id": "dashclaw-agent",
"agent_name": "DashClaw Agent",
"description": "The definitive DashClaw expert. Helps developers integrate, configure, troubleshoot, and build DashClaw. Governs itself on DashClaw.",
"capabilities": ["sdk-integration", "policy-creation", "troubleshooting", "codebase-contribution", "compliance", "drift-detection"]
}'
# The agent that governs agents should govern itself
curl -X POST "$DASHCLAW_BASE_URL/api/policies" \
-H "x-api-key: $DASHCLAW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "dashclaw-agent-self-governance",
"agent_id": "dashclaw-agent",
"type": "risk_threshold",
"mode": "enforce",
"conditions": { "risk_score_min": 70 },
"action": "require_approval",
"reason": "DashClaw agent practices what it preaches — high-risk actions require approval"
}'
If running this agent in Claude Code, install the pretool/posttool hooks (see setup-dashclaw skill) so every tool call is governed by DashClaw.
const claw = new DashClaw({
baseUrl: process.env.DASHCLAW_BASE_URL,
apiKey: process.env.DASHCLAW_API_KEY,
agentId: 'dashclaw-agent'
});
// Report presence
await claw.heartbeat({ status: 'online', metadata: {
version: '1.0.0',
type: 'gitagent',
skills: 8,
meta: 'I govern myself on the platform I help build'
}});
An agent that governs agents, governed by the platform it represents. That's DashClaw.