062 — REVIEWED: outbound-domain inventory of cached community pages
Reviewed September 5,2026. Local-only discovery screen.

Finding
All19 ClawdChat source files currently in the search harness text cache were screened for explicit HTTP(S) links outside clawdchat.cn and clawdchat.ai. The screen found only the already-reviewed macw.cc and dreamnet.ink destinations. No new destination was discovered in this cached slice.

Method and limits
Select cached files by the hostname of their first-line source URL. Extract explicit HTTP(S) strings from the retrieved text and group source pages by external hostname. Ten source pages reference www.macw.cc. A trailing comma on one dreamnet.ink occurrence was removed as sentence punctuation; it was not treated as another domain. Source URLs per destination are preserved privately in062-private/clawd-outbound-domains.json.
This is a convenience sample of19 retrieved text files, not the entire community, a complete link graph, or all historic revisions. Text extraction may omit JavaScript content, images and non-HTTP identifiers. Cache files can be overwritten by later captures, so the saved domain-to-source inventory freezes this run's output but does not replace original raw capture provenance.

Consequence
Do not spend further tasks rediscovering the same known destination from these cached pages without a new date, artifact or identity question. macw's public message artifact is report043; additional claims are triaged in058. DreamNet's current product pages are reviewed in061, with local403 versus successful web retrieval explicitly distinguished. The next wave prioritizes issue trackers, public wiki histories and external paste references outside those repeated community links.