hitl-approval
SkillFiles & storageHuman-in-the-loop approval workflow for high-risk agent operations (file deletions, deployments, config changes).
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the hitl-approval skill
What this skill tells your AI
The instructions your AI receives, as published by nwiizo/ccswarm in .agents/skills/hitl-approval/SKILL.md and read by ahel’s review.
Manage human-in-the-loop approval gates for ccswarm agent operations.
Gates
| Gate | When Required | Risk Level |
|---|---|---|
| plan | Before executing multi-step plans | Medium |
| risky-edit | File deletions, production configs | High |
| deploy | Deployment actions | Critical |
| merge | PR merge operations | High |
Commands
# Request approval
ccswarm approve $ARGUMENTS
# List pending approvals
ccswarm approve list
# Approve with comment
ccswarm approve $ARGUMENTS --id <run-id>
# Reject with reason
ccswarm approve $ARGUMENTS --id <run-id> --reject --reason "explanation"
Risk Levels
| Level | Action | HITL Required |
|---|---|---|
| Low | Read operations | No |
| Medium | Local file writes | Optional |
| High | External modifications | Yes |
| Critical | Production changes | Always |
All HITL decisions are logged to .ccswarm/runs/ audit trail.
Signals
- GitHub stars
- 152
- Forks
- 15
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
hitl-approval- Source
- github.com/nwiizo/ccswarm