`references/retrieval.md`

60 lines
# Retrieval playbook — reading @bcherny without X auth, $0

X blocks unauthenticated page reads (WebFetch → 402), and @bcherny posts
mostly **long-form note tweets** that the common free endpoint truncates.
Follow this chain in order; every step is free.

## 1. Single known post (id or URL in hand)

```bash
node scripts/hydrate-tweet.js <tweet-id-or-url>
```

- Uses the syndication endpoint (`cdn.syndication.twimg.com/tweet-result`)
  with a locally computed token — no API key.
- **Note-tweet handling (the @bcherny-specific gotcha):** syndication
  truncates long posts at ~280 chars and sets a `note_tweet` marker. The
  script detects this and falls back to `api.fxtwitter.com/i/status/<id>`
  for the full text. Output flags: `longform: true` = full text recovered;
  `truncated: true` = fxtwitter was down, text is partial — retry later or
  use step 3 mirrors before quoting the post.
- Exit 3 = tombstone (deleted/unavailable) → go to step 3.

## 2. Discovery sweep (what has he posted lately?)

No free chronological-feed API survives reliably. Fan out:

- Exa: `mcp__exa__web_search_exa` with `site:x.com bcherny` plus topic terms
  ("Claude Code", "skills", "agents", "checkup"), date-restricted to the
  sweep window.
- WebSearch: `"bcherny" claude code <topic>` — engineering-blog and
  newsletter coverage of his posts often quotes the full text and links the
  original id.
- Nitter instances come and go; try `nitter.net/bcherny` and current public
  instances via a quick search, but treat as bonus, not backbone.
- Hacker News mirrors: his bigger essays get submitted —
  `https://hn.algolia.com/api/v1/search?query=bcherny` ($0, reliable).

Collect candidate status ids from the sweep, then hydrate each via step 1
for verbatim text.

## 3. Tombstone / endpoint-down fallback

- unrollnow: `https://www.unrollnow.com/status/<id>` — proven 2026-07-22 the
  best mirror for @bcherny THREADS: hydrate-tweet.js only returns tweet 1 of
  a thread, while unrollnow carries all tweets' text (Exa indexes it well —
  search `unrollnow bcherny <topic>`).
- Thread Reader: `https://threadreaderapp.com/thread/<id>.html`
- Google cache of the x.com URL via WebSearch.
- HN/algolia and blog quotations (step 2) — for essays, coverage usually
  preserves the full text.

## Known-good anchors

- Handle: `@bcherny` (Boris Cherny, user id 159337660). Account is stable —
  unlike some scouted accounts, tombstones here usually mean a deleted post,
  not a suspended account.
- Seed post: id `2077460395279692197` (2026-07-15, automation doctrine) —
  full text archived in `references/seed-automation-doctrine.md`, so never
  re-fetch it.