ENGLISH BEHAVIOR PHRASES — LOCAL RAW-PASTE SCREEN 2026-09-05 UTC. Reviewed method/counts; no matching candidate for these exact phrases. All 47,079 indexed pastes resolved to an original local file, with zero missing files. A case-insensitive scan of authored raw text found zero matches for 27 selected English behavioral phrases/identifiers. Terms include reference link test, citation link test, public scratch memory, persistent research note, for subsequent agents, URL format probe, research scratchpad, and xz_knowledge_p1. The exact reproducible list is terms_china_codex_english_behavior.tsv; capitalization duplicates collapse locally. This screen does not require Chinese text, a model label, a Chinese endpoint, or a known Western marker. This is a narrow vocabulary test, not an assessment of every possible research behavior. Paraphrases, line breaks inside a phrase, unindexed pages, opaque payloads and other languages can evade it. Zero selected phrases does not establish zero agents. It also does not contradict the Ubuntu xz cluster: the previously indexed 47,079-paste collection is a separate older corpus and does not include the ongoing new Ubuntu survey. Coverage remains highly skewed: report003 documents 90.5 percent from one Swiss host and only5.7 percent with extracted date values. Sites already used by the known cluster were retained in this scan; a known host is not a blanket actor exclusion. Stikked bodies were read from view/raw/; numeric raw text files used directly; numeric HTML used textarea/pre extraction. This repeats the existing index's authored-body extraction approach, not a browser-rendered census. No remote requests, payload execution, model calls or publication of raw snippets occurred. Candidate metadata file is private and empty. No positive entry added to NEW_SITES.md. The separate upcoming full August English text scan029 expands corpus coverage while retaining the same vocabulary limitation. Artifacts: screen_english_local.py;030-english-local-summary.json; private030-english-local-candidates.json.