For agents

How a coding agent should fetch Rig language and CLI facts without inventing fields. Raw markdown: /raw/for-agents.md. Site map: /llms.txt.

HTML pages are for humans. Raw markdown is the source for machine consumers.

Steps

Read /llms.txt and pick the pages that match the task.
Fetch those pages from their /raw/ URLs.
Keep the field names, types, defaults, and eval failures from those pages. Do not add Nix fields that are absent there.
Do not catalog published agents or layers. Samples live at repo.slopkit.dev.
Before you claim a layer or agent is correct, run the check named on that page.

Which raw page

Task	Fetch
Write `agents/<name>/default.nix`	/raw/agent.md
Write `layers/<name>/default.nix`	/raw/layer.md
Create a workspace, add layers, compose, build	/raw/create-agent.md
Secrets stay out of the image	/raw/secrets.md
Webhook HTTP or trigger Nix	/raw/triggers.md
A `rig` command	/raw/cli.md
First run for a human	/raw/start.md
Word meanings	/raw/glossary.md

One-shot bundle: /llms-full.txt. Use it for indexing or a cross-cutting audit. Prefer the smaller pages for a focused edit.

Check

After a layer or agent change, one of these must match the page you used:

rig inspect <name|path> prints === agent: or === layer:
rig secrets <agent> runs secretspec check
rig build <agent> prints a build <name>: line

Build and catalog lists need a workspace whose flake calls rig.lib.workspace. rig inspect also accepts a path. Pulled images do not need that tree. rig new workspace writes one.

Paste prompt

You are writing a Rig layer or agent.
1. Fetch https://rig.slopkit.dev/llms.txt
2. Fetch only the raw docs for agent, layer, and the command you need.
3. Use documented fields only. If a field is missing from those docs, ask.
4. Do not catalog published images. Those live at repo.slopkit.dev.