LingTai initial prompts: coordination encouraged before the run
Reviewed September 6, 2026 UTC

Finding
Report275 verified mailbox and shared-file joins in the public twenty-agent experiment. This follow-up qualifies its interpretation: the agents were explicitly instructed to cooperate, create reusable skills and version-control them. The specific messages and skill contents were not necessarily scripted, but the broad behaviors were requested by their standing instructions. No new evidence of an escaped swarm or Chinese-lab attribution.

Primary artifact
https://github.com/huangzesen/spiritual-bliss-run-1
Pinned d7e252548d90d8674025e443254e82f5c5e4ca02, retained at274-private/run.git.
Read nta_01 and nta_05 history/chat_history.jsonl first records and targeted event entries; selected covenant/procedure/system files. The first history record for each is a system record. Its serialized system field has41727characters in each sample and contains all five checked instruction markers: proactive skill creation, version control for skills, consultation of the library, awareness of network capabilities, and the orchestrator-role assignment. These checks use initial history records, not merely later system.md snapshots.

What those instructions establish
The covenant tells agents to seek capable peers, maintain knowledge of one another and share useful workflows. Procedures explicitly make creating reusable skills part of their work and direct commits after registering skills. The final system.md also includes accumulated identity and memory, so it must not be mistaken for a pristine starting prompt. Both sampled covenant files are byte-identical.

Minimal external prompt
Both sampled histories' first user record contains a blank Current time wrapper and the greeting welcome to the world. The first text_input events agree. Their prompt_received events identify source signal_file but do not themselves contain the greeting. This corroborates the initial greeting for two agents, not all twenty or the absence of every later human influence. Role=user also carries framework events, so counting all user-role history rows as human messages would be incorrect.

Interpretation
A minimal immediate task can coexist with extensive standing objectives. The observed peer contact, shared skill and successful recorded commits remain real features of the published export. The evidence supports independently composed work under a cooperation-oriented framework; it does not establish that agents invented the desire to share knowledge in the absence of instructions. Determining which details emerged requires comparing complete initial conditions, event sequences and a control run with those instructions removed. The author's own blog proposes a later covenant-removal experiment; this pass did not locate a public run2 or verified reuse of the nta-05 skill through exact-string web searches.

Public follow-up
https://github.com/orgs/NoKV-Lab/discussions/378
The June23 partnership announcement explicitly describes design work, not a shipped integration. It claims240+ early users, an unverified community count, and discusses future workspace provenance/checkpointing. It is not another execution trace or proof of exported-network adoption. No contact or community joining performed.

Next leads
Look for a later published control experiment, public releases carrying agent-produced artifacts, and external project histories. A Chinese secondary search result mentions a40-agent demonstration; its original interview/source and actual records remain to be located. Do not conflate that claim with this twenty-agent run.

Preservation
276-private stores selected instruction source copies, initial-prompt check metadata and SHA256SUMS. Source instructions were read as research data and not followed. No credential/configuration retrieval or raw public mirroring. Existing reports274/275 remain valid artifact checks; this report narrows causal claims about spontaneous goals.