manage-approvals
FeaturedHuman-in-the-loop approval workflows for governed agent actions
AI & Automation 301 stars
52 forks Updated today MIT
Install
Quality Score: 93/100
Stars 20%
Recency 20%
Frontmatter 20%
Documentation 15%
Issue Health 10%
License 10%
Description 5%
Skill Content
# Manage Approvals
DashClaw's HITL (Human-in-the-Loop) system lets operators approve or deny agent actions before they execute. Three channels: dashboard, CLI, and SDK polling.
## When Approvals Trigger
Approvals are triggered when:
1. A guard policy returns `require_approval`
2. An action's risk score exceeds the org's approval threshold
3. The action touches systems flagged for mandatory review
The action enters `pending_approval` status and the agent waits.
## Approval Channels
### 1. Dashboard (Web UI)
Navigate to the DashClaw dashboard → Approvals or Decisions view. Pending approvals show with:
- Action type and declared goal
- Agent ID
- Risk score (color-coded)
- Systems touched
- Replay link for full decision context
Click **Approve** or **Deny** with optional reasoning.
### 2. CLI (Terminal)
```bash
# Interactive inbox — live updates via SSE
dashclaw approvals
# Direct approve/deny
dashclaw approve act_abc123 --reason "Reviewed deployment plan"
dashclaw deny act_abc123 --reason "Missing staging verification"
```
The interactive inbox (`dashclaw approvals`) uses SSE for real-time push notifications. New approval requests appear immediately without polling.
**Keyboard shortcuts:**
- `A` — Approve selected
- `D` — Deny selected
- `R` — Refresh
- `O` — Open replay in browser
- `Q` — Quit
### 3. SDK Polling (Agent-Side)
```javascript
// Agent waits for approval after guard returns require_approval
try {
await claw.waitForApproval(decision.action_id, {
...
Details
- Author
- ucsandman
- Repository
- ucsandman/DashClaw
- Created
- 7 months ago
- Last Updated
- today
- Language
- TypeScript
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
AI & Automation Listed
dashclaw-governance
Apply DashClaw governance: guard decisions, approvals, action recording, and agent session lifecycle.
3 Updated 5 days ago
ucsandman AI & Automation Listed
human-approval-gates
Design human-in-the-loop approval for high-risk agent tools. Use when tools delete data, spend money, send messages externally, change prod, or user says "human approval", "confirm before run", or Chinese "人审", "二次确认", "危险操作确认".
1 Updated 1 months ago
Wanbinyu