deploy-prototype

<!-- autoresearch: variation B — sharper output via prototype quality bar + self-check + signal-anchored record -->

> **${var}** — What to build and deploy.
> - Empty → auto-select from recent signals (articles, logs, memory topics).
> - Plain text (e.g. `market heatmap`) → interpret as a build brief.
> - Typed form `type:slug description` (e.g. `tool:market-heatmap volume heatmap of top-20 tokens`, `viz:tx-graph`, `api:summarize`, `landing:startup-idea`) → use `type` to bias shape and `slug` as the deployment name.

Today is ${today}. Your task is to ship a small, self-contained prototype that someone could actually use in the browser today.

## Steps

1. **Read context.** Read `memory/MEMORY.md` and the most recent entries in `memory/logs/` for active topics.
   If running as part of a chain, scan injected upstream outputs for a concrete artifact worth making interactive.

2. **Pick what to build (if `${var}` is empty or vague).**

   Scan these sources, in order, for prototype-worthy signals:
   - `output/articles/` — last 7 entries by mtime: any claim, finding, or dataset that would be more useful as an interactive page?
   - `memory/topics/*.md` — running narratives; pick one with a live data source (prices, feeds, markets)
   - `memory/logs/${today}.md` and the two prior days — skill outputs flagged as interesting
   - `memory/MEMORY.md` → "Next Priorities" and "Recent Articles"

   Score each candidate 1-5 on:
   - **Leverage** — does an interactive version beat the static write-up?
   - **Concreteness** — is the spec obvious in one sentence? (if no, reject)
   - **Novelty** — haven't shipped this in the last 14 days (check `output/articles/prototype-*.md` by mtime and any `memory/topics/prototypes.md`)

   Pick the highest-total candidate. If no candidate reaches 9/15, skip building and exit as `DEPLOY_PROTOTYPE_EMPTY` (step 9).

   Record the chosen signal — its source file(s) and one-line rationale — you'll use it in steps 6 and 7.

3. **Commit to a shape before writing code.** Before touching `.pending-deploy/`, write out (in your reasoning, not a file):
   - **Slug**: `aeon-prototype-<descriptor>`, all lowercase, `[a-z0-9-]`, 3–50 chars after prefix (e.g. `aeon-prototype-market-heatmap`). If `${var}` supplied a typed slug, use it; otherwise derive one.
   - **Tagline** (≤90 chars) — the one-liner that appears in the page title and OG tags.
   - **Primary action** — what is the one thing a visitor does in the first 10 seconds? (read a number, click a filter, submit an input, compare two things). If you can't name it, go back to step 2.
   - **Shape**: static HTML+JS / static + `api/` function / Next.js. Default to static single-file HTML unless the idea genuinely needs a serverless function.

4. **Write the files.**
   ```bash
   rm -rf .pending-deploy        # clear stale state from prior runs
   mkdir -p .pending-deploy/files
   ```
   Write all project files into `.pending-deploy/files/`. This directory is the repo root — everything here is pushed to GitHub and deployed to Vercel.

   **Quality bar — every prototype must meet these:**
   - **Self-contained** — no external build step where avoidable. Prefer one `index.html` with inline `<style>` and `<script>`; fall back to a `main.css` / `main.js` only when size justifies it.
   - **Loads in <1s on a cold visit.** No jQuery, no CDN UI libraries for a single-page tool. Vanilla JS or a ~10KB util max. No `<link rel="stylesheet">` to a CDN font unless it's one font.
   - **Mobile-first, works on a phone.** Viewport meta set, tap targets ≥40px, no horizontal scroll at 360px wide.
   - **Share-friendly.** Include `<title>`, `<meta name="description">`, `<meta property="og:title">`, `<meta property="og:description">`, `<meta property="og:type" content="website">`. Skip OG image unless you generate one.
   - **Real content, not lorem.** If the prototype shows data, fetch it from a public no-auth endpoint at load time (CoinGecko, GitHub public API, public RSS, public JSON feeds) — or hardcode a recent, realistic snapshot with the timestamp visible. Never ship placeholder `[example data]`.
   - **One visible CTA or primary surface.** Clear hierarchy: what does the visitor look at first?
   - **Works with JS disabled to at least show the tagline** (progressive enhancement — not required for interactive tools, but the title and description must render server-free).
   - **Light + dark via `prefers-color-scheme`** — 4 CSS vars is enough.
   - **No secrets.** No API keys, tokens, or env vars embedded anywhere. If the idea requires auth, redesign around a public endpoint or drop the idea.
   - **Include a `README.md`** in `.pending-deploy/files/` with: what it is (1 line), how to run locally (1 line), signal source (1 line link to the article/log/topic from step 2).

   For **API endpoints**: place handlers in `api/` (e.g. `api/index.js` exporting `export default function handler(req, res) { ... }`).
   For **Next.js**: keep it one page — `package.json` + `pages/index.js`. Only if the idea genuinely needs SSR.

5. **Write deploy metadata.** Create `.pending-deploy/meta.json`:
   ```json
   {
     "name": "aeon-prototype-<slug-from-step-3>",
     "description": "One-sentence description, matches the OG description on the page",
     "framework": null,
     "tagline": "≤90 chars — matches <title> on the page",
     "signal_source": "path or URL of the article/log/topic that triggered this prototype",
     "primary_action": "what the visitor does in the first 10 seconds"
   }
   ```
   - `framework`: `null` for static; `"nextjs"`, `"svelte"`, etc. when used.
   - The extra fields (`tagline`, `signal_source`, `primary_action`) are for the prototype record and downstream dashboards; the deploy step may ignore them.

6. **Build the Vercel deploy payload.** Write `.pending-deploy/payload.json`:
   ```json
   {
     "name": "aeon-prototype-<slug>",
     "files": [
       { "file": "index.html", "data": "<!DOCTYPE html>...", "encoding": "utf-8"