Watch explicitly named stale runs and auto-resume them; pass --all to opt into a workspace-wide sweep. Run `smithers supervise --help` for usage details.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add smithersai/smithers --skill smithers-supervise --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Smithers Supervise?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/smithersai-smithers-supervise-smithers)More formats (shields.io, HTML) on the badges page.
---
name: smithers-supervise
description: Watch explicitly named stale runs and auto-resume them; pass --all to opt into a workspace-wide sweep. Run `smithers supervise --help` for usage details.
requires_bin: smithers
command: smithers supervise
---
# smithers supervise
Watch explicitly named stale runs and auto-resume them; pass --all to opt into a workspace-wide sweep.
## Options
| Flag | Type | Default | Description |
|------|------|---------|-------------|
| `--run` | `string` | | Only supervise these run IDs (comma-separated) |
| `--all` | `boolean` | `false` | Explicitly supervise every eligible run in the workspace |
| `--dryRun` | `boolean` | `false` | Show which stale runs would be resumed, without acting |
| `--interval` | `string` | `10s` | Poll interval (e.g. 10s, 30s, 1m) |
| `--staleThreshold` | `string` | `30s` | Heartbeat staleness threshold before resume |
| `--maxConcurrent` | `number` | `3` | Max runs resumed per poll |
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
