257 — Chinese novelist repository: swarm label, chapter artifact and local text generators
Reviewed2026-09-06 UTC. Bounded new lead; no verified multi-agent execution.

PRIMARY
https://github.com/LunaticLegacy/novelist
Search found this Chinese novel-writing package through its literal English agent swarm description. Current recursive tree2b6a7d0c580b07c7b1d5321536b3527d4b34db4e has86 entries, nontruncated. It contains writing templates/scripts, two outline files, one chapter file正文/第001章.md (11,522 bytes) and a storyboard. No separately named agent-message log or run transcript was identified in the filename inventory. Chapter prose was not read or reproduced.

SOURCE CHECK
Five small files fetched at the pinned revision were Git-blob verified: README.md, references/draft-template.md, agents/openai.yaml and two tools/generate_*.py scripts.
README recommends a user prompt requesting chapters1–8 sequentially with state updates, attributes the original package to PenglongHuang/chinese-novelist-skill, and describes local planning and validation. agents/openai.yaml is skill-interface metadata, not evidence of OpenAI ownership or execution. Investigated instructions were treated as data and not followed.
Both generator scripts parse successfully as Python source. Their imports are standard-library re/pathlib, with csv in one script. Static AST inspection shows local chapter construction, text-length management, story-state updates and file writes. Predefined text fragments and extension/padding functions are present. No model API invocation or worker spawning was identified in these two scripts. They were never executed.
This matters because named chapter/state files can be produced by ordinary deterministic scripts. The current artifacts do not establish which process created the committed first chapter; this check did not compare it against generator output or reconstruct history. Do not call the novel output fabricated or a verified swarm product.

DE-DUPLICATION
Broader searches also returned kvcache-ai/AgentENV and duanyytop/agents-radar, already covered in204 and185. Those were not counted as new discoveries. AgentENV's Kimi association and network configuration are not new evidence of an escaped actor.

ASSESSMENT / NEXT
The repository supplies Chinese writing-workflow material and concrete local content files, but not authenticated teamwork, unattended publication, public scratch-memory use or lab attribution. Lower priority unless the author links raw multi-agent transcripts or a separately traceable published work. Maintain the original lab/public-surface objective rather than equating every agent-swarm phrase with a positive finding.

CAPTURES
257-private/tree.json, five verified files and SHA256SUMS. Public read-only requests; source parsed as data without executing code.