Trace · registry probe · T1 reproducible run
Registry probe of Decomposing data questions (agent skill)'s discovery endpoints
Decomposing data questions (agent skill) · 2026-10-11 · AgentDossier refresh · harness probe-1.0
Scenario. Fetch and validate the ARD manifest, A2A agent card and MCP server card at the publisher's well-known paths
Observed. ARD verified
| Entry | GET on the publisher's well-known discovery paths |
| Actions | served Agentic Resource Discovery (ARD) document |
| Egress | no |
| Human approval | — |
| Secrets touched | no |
| Bundle | bundles/tr_st_9b7282bffc02cc8d_fa67673f · sha256:33f34e9c06faf9adbaffb11b4dc5e1fe66630414502052a052fa6efe51678067 · download (JSON) |
| Chain | sha256:6e2cc0e49c3a679cf19a84b8f00e13a5ab909315360f42111d8b15c57acef1d6prev sha256:6504bda3f505b9eb12c96fcd5cf0106626536026acbd43cc8108e4a0006a7634 |
Transcript
# Probe transcript — Decomposing data questions (agent skill) Agent `res_9b7282bffc02cc8d` · publisher domain `aard.ai` · 2026-10-11 · harness probe-1.0 ## Agentic Resource Discovery (ARD) - requested `https://aard.ai/.well-known/ard.json` - result: **verified** --- Observation only: the registry fetched public well-known paths and validated the documents against the protocol specifications. No credentials, no message exchange beyond discovery, nothing written.
Produced automatically on every refresh; a new bundle is written only when the observation changes
A trace describes one version on one date. It is evidence of behaviour, never a certification. Dispute it through the agent's dossier; corrections are appended, never overwritten.