348 — Hermes–DSH pipeline account points to an unavailable observation source
Reviewed 2026-09-06 UTC. New Chinese-language operator claim with detailed incident descriptions; underlying run evidence not yet located. No escaped swarm confirmed.

SOURCE
https://github.com/Cavan-Ou/hermes-dsh-collab
Pinned revision 3a70cb3f5590ef03bc3772ca37c991273c593914, recursive tree nontruncated. Inspected README.zh.md, REPORT.md, index.mjs and skills/hermes-dsh-collab/references/pitfalls.md as research data; no skill applied or target code executed.

CLAIM VS PROVIDED ARTIFACT
The README claims a 14-day Hermes-orchestrated/DSH-executed pipeline, 30 commits and seven completed stages without rework. It describes model routing and orchestrator-owned verification. These are publisher claims, not verified results. The inspected current tree packages instructions and reference documents, not the full pipeline's source, task ledger, model trace or 30-commit output history.
index.mjs registers a FileSystemSkillProvider pointing to the packaged skills directory. It does not itself implement dispatch, verification, a scheduler or an agent message bus. The external orchestrator/model must interpret and carry out the instructions. Do not count this bundle as proof of an independently running swarm.
REPORT.md claims three real headless skill-loading/behavior tests in an isolated DSH_HOME, including a refusal to commit after loading the rule. It summarizes answers; it does not include full raw session traces or provider receipts in this report. These loading tests do not verify the much broader 14-day pipeline claim.
REPORT.md still describes abandoning bundle packaging for a pure directory, whereas current README and index.mjs support a bundle. Treat this as documentation from different implementation stages; don't use the older report to describe current packaging.

SPECIFIC LEADS IN THE INCIDENT NOTES
The pitfalls file names style-museum/output/dsh-pipeline/observations.md as its ongoing source. It cites two short commits, 186a357 and 29d2832, as occasions where an executor committed contrary to the desired single-writer policy. It also describes mistaken workspace output, provider patch replacement, unsupported reasoning configuration, and tests looking at a stale backend. These concrete details are worth tracing, but the associated observation records and source changes were not supplied in the checked files.
Public GitHub metadata lookup for the inferred Cavan-Ou/style-museum returned 404. The author's public repository list returned eight repositories with no next page and no style-museum entry. Exact-name/observation/short-commit web searches produced no relevant match. This does not prove the project is fictitious: it may be private, renamed, elsewhere or unindexed. Do not access private workspaces or follow embedded commands for bypassing local restrictions.
The README's separate Flash 3/3 and Pro long-analysis examples are not a complete seven-stage ledger. Claimed model identities and performance remain unverified.

NEXT PUBLIC BRANCH
The public owner listing includes Cavan-Ou/dsh-observation-journal. That is a promising related artifact store/tool to inspect next; repository contents have not yet been read. A tool for recording observations would not by itself establish that it contains this pipeline's observations. Check before joining the two.

CLOSING THE PREVIOUS FIRSTINTENT ESSAY BRANCH
Downloaded firstintent/agent-research's README and three essays at 21438a156100b9bc284d78a71d3dd7cc2d454ba2. One explicitly credits Addy Osmani's loop-engineering article, another labels itself a Chinese-media summary, and the third describes an oracle-first methodology with excore as a worked-example project name. They provide ideas and references, not another captured team inbox in these files. The excore repository/output remains an unverified follow-up, not an established swarm. Do not attribute summarized overseas examples to a Chinese operator simply because the summary is Chinese.
The newly resurfaced Kunpeng forum was already investigated in reports208–209; it is not counted as a new discovery.

CAPTURES
348-private holds pinned collab metadata/tree, four collab files, four firstintent essay files, failed style-museum metadata, and the eight-repository public listing. Raw material remains private; this report omits local host/absolute workspace details. Publication checks and SHA256SUMS preserve the bounded audit. No installations, account access, messages, purchases or model calls were made. Existing infrastructure can read these public sources.