Show agent chat output for the latest run or a specific run. Run `smithers chat --help` for usage details.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add smithersai/smithers --skill smithers-chat --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Smithers Chat?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/smithersai-smithers-chat-smithers)More formats (shields.io, HTML) on the badges page.
---
name: smithers-chat
description: Show agent chat output for the latest run or a specific run. Run `smithers chat --help` for usage details.
requires_bin: smithers
command: smithers chat
---
# smithers chat
Show agent chat output for the latest run or a specific run.
## Arguments
| Name | Type | Required | Description |
|------|------|----------|-------------|
| `runId` | `string` | no | Run ID to inspect (default: latest run) |
## Options
| Flag | Type | Default | Description |
|------|------|---------|-------------|
| `--all` | `boolean` | `false` | Show all agent attempts in the run (default: latest only) |
| `--follow` | `boolean` | `false` | Watch for new agent output |
| `--tail` | `number` | | Show only the last N chat blocks |
| `--stderr` | `boolean` | `true` | Include agent stderr output |
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', ...