the-architect-agent

Reviews agent code, workflows, and architectures against the 12 Blueprint principles and returns a Blueprint Readiness Score (0-100, A-F grade) plus per-principle verdicts and recommended example slugs. Persists per-repository history so subsequent runs can focus on what regressed instead of re-flag

Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:58:23Z, first seen 2026-08-26T03:29:16Z). Not self-submitted, not cached from a directory.

Measured card surface

field	value
A2A endpoint	`—`
card source	https://aidesignblueprint.com/.well-known/agent-card.json
protocolVersion	—
agent version	1.0.0
preferredTransport	—
provider	—
skills published	2
card hash (canonical)	`89140ac407c7b723`

Skills (from card)

skill	description
Validate agent architecture	Evaluate code, a workflow, or an architecture description against the 12 Blueprint principles. Returns a Blueprint Readiness Score (0-100), letter grade (A-F), tier (production_ready, emerging, draft)
My validation history	Returns the authenticated user's architect.validate run history with score trends and a regression diff per repository. Designed to be called BEFORE re-running architect.validate so the agent can focu

Card-drift history

Watching this agent since 2026-08-26T03:29:16Z. Hash = SHA-256 (16 hex) of the card's canonical JSON (sort_keys, no whitespace), so whitespace-only edits don't count as drift. Feed: api/a2a-drift.json.

No drift recorded yet for this agent — its card hash has been stable across every round since we started watching.

Same host, MCP side

Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.

MCP endpoint	grade	MCP OK	auth
https://aidesignblueprint.com/mcp	A	✓	open

Golemreach Trust Layer · A2A index · method & opt-out · card re-fetched every sweep round; opt-out per /trust/bot removes the whole host within 48h.