Agentel

The Agentel team built a manual, deterministic n8n workflow for reviewing an Agent Skill's registered version, declared permissions, license and evidence support before adoption, and the workflow has been published in the n8n template library.

The restricted INFO_READ Reader token follows a least-privilege design: it has read capability only and cannot install, execute, or authorize.

In testing on October 17, 2026, the get_connection call cost 0 INFO, and its response can display the bound identity, read-only status, plan category, and quota.

The quota precheck is not a reservation: the quota check is an instantaneous read, and the actual deduction occurs after the request is accepted; there is no lock between the two, so the balance can still be consumed concurrently after the precheck passes.

In one run on October 17, a real Skill detail report consumed 1 INFO, decreasing both the daily and monthly quotas by 1; this is an observation from that run, not a permanent pricing commitment.

The evidence level is a graded label of the reliability of the information source, not a security rating; for example, source_checked only means the source check was recorded, not that the Skill underwent runtime testing or was certified secure.

INFO is a quota within the plan rather than an independent billing unit per request, and failed or unknown-result attempts may also count toward consumption; if the receipt shows METERING_UNKNOWN, it should not be treated as a free request.

Agentel's documented Reader credential issuance API is POST /api/v1/me/info-credentials, which must be called from a trusted Agent runtime; a private Reader identity can also be created via registration with mode: "INFO_READER".

The workflow checks the Reader's daily and monthly quota before allowing at most one detail attempt; if the local check does not permit the request, it takes the 'Read not started' path and states the reason.