Skip to content

docs: add agent harness integration guidance #31

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
decimozs merged 2 commits into from
Jun 8, 2026
Merged

docs: add agent harness integration guidance #31

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a7c1206
docs: add agent harness integration guidance to getting-started and a…
decimozs Jun 8, 2026
f3f3b4d
feat(docs): add rainbow banner announcing agent skills support
decimozs Jun 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions apps/docs/content/docs/reference/agent-skills.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,3 +27,13 @@ The skill covers:
- Debugging failing test cases
- Judge provider configuration
- Run comparison via `history --diff`

## Agent harness integration

Type `/regtrace init` inside an agent harness (OpenCode, Claude Code, Cursor,
Zed, Aider, etc.) to bootstrap regtrace without writing config by hand. The
agent scans your project for LLM signals — prompts, client calls, RAG chains,
tools, and API routes — then generates golden sets and config wired to your
actual code.

See `skills/regtrace/SKILL.md` for the full workflow.
7 changes: 7 additions & 0 deletions apps/docs/content/docs/tutorials/getting-started.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,13 @@ This creates:
- `.env.example` — template with commented API key placeholders
- `.regtrace/runs/` — local run storage

<Callout type="tip">
**Using an AI coding agent?** Run `/regtrace init` in OpenCode, Claude Code,
Cursor, or Zed to auto-detect LLM calls in your project and generate
tailored golden sets — no manual editing needed. See the
[Agent Skill](/docs/reference/agent-skills) reference.
</Callout>

## Inspect the golden set

Open `golden-sets/qa.yaml`. It contains two test cases:
Expand Down
4 changes: 4 additions & 0 deletions apps/docs/src/app/layout.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import { RootProvider } from "fumadocs-ui/provider/next";
import "./global.css";
import { Analytics } from "@vercel/analytics/next";
import { Banner } from "fumadocs-ui/components/banner";
import type { Metadata } from "next";
import { Inter } from "next/font/google";

Expand Down Expand Up @@ -29,6 +30,9 @@ export default function Layout({ children }: LayoutProps<"/">) {
return (
<html lang="en" className={inter.className} suppressHydrationWarning>
<body className="flex flex-col min-h-screen">
<Banner id="agent-skills" variant="rainbow">
Agent Skills are now supported for Regtrace!
</Banner>
<RootProvider
theme={{
defaultTheme: "light",
Expand Down
Loading