harbor-sandbox-operator-loop

Original：🇺🇸 English

Translated

Execute Harbor capabilities, handle grant and approval flows, manage secrets, and operate the execution lifecycle. Use when asked to run a capability, execute a Harbor action, handle an approval_required response, manage secrets, or check execution status.

18installs

Sourcezonko-ai/harbor-skills

Added on2026-04-01

NPX Install

npx skill4agent add zonko-ai/harbor-skills harbor-sandbox-operator-loop

SKILL.md Content

View Translation Comparison →

Use this skill when the agent needs to execute a Harbor capability, handle grant/approval gates, or manage the execution lifecycle.

Rules

Use Harbor CLI or API only.
Never bypass Harbor by calling backing providers directly.
Treat published capabilities as the only executable source of truth.
If Harbor requires a grant or execution approval, explain the pending step and wait.
Use capability-first language: capability, grant, approval, execution. Not provider, connector, tool.

Execution loop

Confirm identity and reachability:

harbor auth whoami --plain

and

harbor status --plain

List available capabilities:
```
harbor ls --plain
```
.
Inspect the target capability:
```
harbor inspect <capability> --plain
```
.
Check the capability state:
- ```
ready
```
  — execute directly.
- ```
approval_required
```
  — a grant is needed. Execute to trigger the grant request, report the
```
approval_id
```
  , tell the user to approve at
```
https://dash.tryharbor.ai/approvals
```
  , then retry.
- ```
secret_missing
```
  — the capability needs owner-managed secrets. Use
```
harbor secrets ls --plain
```
  to check, then
```
harbor secrets set <name> --value <value> --plain
```
  to provide them. Or tell the user to set them in the dashboard.

Execute the capability:

harbor <capability-slug> --<arg> <value> --plain

If the execution returns
```
approval_required
```
, report the
```
approval_id
```
and wait for the user to approve.
After approval, retry the execution.

Secret management

List secrets:
```
harbor secrets ls --plain
```
Inspect:
```
harbor secrets inspect <name> --plain
```

Set:

harbor secrets set <name> --value <value> --plain

Delete:
```
harbor secrets delete <name> --plain
```

Historical note

The old

sandbox.run

sandbox.status

, and

sandbox.logs

commands are deprecated.

compute.modal

is the closest published compute capability. Run

harbor ls --plain

to see current capabilities.

See

references/sandbox-loop.md