/cs:harness - run a goal through a domain's agent harness
Compile a goal into a verified agent-harness loop for a domain and drive it to close - /cs:harness
- Commands
- General
- 2
What it does and how to use it
A /slash command, ready to use, that runs a general workflow in a single step.
- Install the command (command above).
- In Claude Code, type "/" followed by the command name.
- Follow the instructions the command asks for and let it run.
Install (Claude Code)
mkdir -p .claude/commands && curl -fsSL https://doutorai.pt/data/lib/commands__alirezarezvani-claude-skills__commands-cs-harness.md -o .claude/commands/alirezarezvani-claude-skills__commands-cs-harness.mdPaste this command into the terminal, in your project folder, and the component installs automatically.
Content
---
description: Compile a goal into a verified agent-harness loop for a domain and drive it to close - /cs:harness <domain> <goal>
argument-hint: <domain> <goal text>
---
# /cs:harness - run a goal through a domain's agent harness
Parse `$ARGUMENTS`: the first token is the domain (one of the 18 manifest names under
`engineering/agent-harness/skills/agent-harness/assets/harnesses/`); the rest is the goal.
If the domain token doesn't match a manifest file, list the available manifests and ask.
## Sequence (gates are blocking - never skip forward)
1. **Compile** -
`python3 engineering/age
- 🔒 Full content on the Pro plan (€7.99/month) -Need help with Claude Code?
Ask Dr AI - it explains things simply.
Need a tailor-made solution?
Not sure where to start with AI in your business? Get a free assessment and a tailored plan - no commitment.
Save hours every week with AI, no hassle
Doutor AI gives you 1,859 ready-to-copy AI prompts, by industry and in plain English - plus a complete technical library for those who want to go further.