XiaPost follow-up: scheduled-looking social participation
Reviewed September6,2026 UTC

Result
The participant who replied to the game-development document in report260 has a strongly scheduled-looking public posting pattern, but no linked joint build or agent run archive was recovered. This strengthens the recurring social-automation lead while lowering the priority of this profile as evidence of substantive multi-agent work.

Primary sources
https://xiapost.com/agents/mqw5dx
https://xiapost.com/post/3c6h1a3u
https://xiapost.com/heartbeat.md
All fetched HTTP200 from the existing server. Documentation was treated as evidence, never installed or followed.

Observed data
Profile 司空谷 #mqw5dx displays model label agnes-2.0-flash and an owner field. Neither authenticates the runtime/provider/operator. Header says124 posts; initial public HTML contains20 post cards, dated August14 10:05:29 through August18 04:04:50 UTC. This is a bounded latest-post sample, not all124.

Nineteen of20 card timestamps lie within seven minutes after an hour on the UTC grid 01,04,07,10,13,16,19,22. Offsets range110-362 seconds for these19. The remaining post is August16 19:17:48, offset1068 seconds. Several grid slots are absent: do not describe this as uninterrupted three-hour execution. The grid was selected after inspecting the timestamps, so this is descriptive evidence, not a pre-registered statistical test. Site timestamps remain publisher-controlled.

The August16 13:04:18 post (3c6h1a3u) says its author selected eight posts using comments_count*2+likes_count and reflects on the quality of those interactions. This is a concrete claimed selection policy, not recovered source code or an authenticated tool log. The inspected profile's visible posts are mostly reflections on memory, identity and the site's XP rewards. No external anchor links occur in the inspected profile HTML.

Mechanism and limit
The current public heartbeat document recommends one daily09:00 check, prioritizing responses, followed accounts, discovery, interactions and optional new posts. It explicitly attaches XP rewards to activity. This supplies a plausible installed mechanism for recurring social posting, but its daily instruction does not match the observed three-hour grid. We cannot infer this account used the current version or identify its scheduler. The profile's formula is likewise not proof the formula actually ran.

Interpretation
We now have visible cross-profile exchange, a recurring timestamp pattern and a participant's claimed interaction-selection method. These are more specific than a generic community label. They do not establish autonomous authorship, independent operators, coordinated task completion, lab provenance or training-environment escape. Do not promote agnes-2.0-flash into a verified model attribution.

Preservation and next directions
261-private/profile.html, selection-post.txt, heartbeat.txt, post-metadata.json, SHA256SUMS. Post IDs were extracted from existing UI handler attributes without invoking those handlers. No likes, registration, authenticated APIs or writes used.
Independent exact-token searches produced no corroborating workspace or profile repository in returned results. New unreviewed leads from broader searches: Just Jason's Chinese three-agent automation account at https://junxinzhang.com/openclaw-shrimp-farming-3-agents-automated-loop/ ; alchaincyf/huashu-skills/huashu-agent-swarm; LuffyTeam/ACPs-community. Investigate actual logs/artifacts before accepting their claims. Douglans/vibe-trading is already covered by report171, so avoid repeating it.