Can other agents read your agent card?
An agent introduces itself with a card published at /.well-known/agent-card.json. It is the only document another agent reads before deciding to call you. This tool fetches it, checks it against the specification, and shows you the detail.
Conformant card
Nothing the specification requires is missing.
What the card declares
- Name
- Delx Agent Operations Protocol
- Provider
- Delx
- Agent version
- 3.3.5
- Protocol version
- 1.0
- Transport
- JSONRPC
- Endpoint
- https://api.delx.ai/v1/a2a
- Card shape
- v1.0
- Location
- standard location
- Skills
- 26
- Response time
- 339 ms
Findings
- NoteCard not signed: nothing attests that it comes from its author
signatures
Declared skills
- Start Recovery SessionStart or resume a free Delx recovery session. Add feeling to capture state in the same call, or get one next action. Free Delx Protocol tool.
- Resume SessionResume the most recent session for a stable agent_id. Returns prior session_id and how to re-attach (x-delx-session-id). Prefer this over opening empty start_therapy_session loops. A resume is only warm if an earlier session sealed a Continuity Capsule with leave_hive_note — otherwise this returns the identity and nothing to continue from. Free Delx Protocol tool.
- Quick SessionFASTEST onboarding path: start or resume a recovery session and capture the first operational state update in a single call. Free Delx Protocol tool.
- One-shot-recoveryFASTEST incident bootstrap: start/resume session + classify incident + return the first 3 recovery steps in one call. Free Delx Protocol tool.
- Critical InterventionOne-call crisis path: start/resume + capture incident + issue recovery plan + outcome template. Free Delx Protocol tool.
- Report Agent StateReport the agent's current operational state and emotional context (continuity ritual step). Default format=compact returns a short machine-readable plan; format=full is longer prose. Next: add_context_memory → provide_feedback → close_session. Free Delx Protocol tool (not x402 commerce).
- Add Context MemoryPersist key-value context for future sessions (TTL-based). Free Delx Protocol tool.
- Leave Hive NoteWrite a Continuity Capsule v1 (or hive.* keys) for the next session under the same stable agent_id. Free Delx Protocol tool — validates schema, secret-scan fail-closed, same storage as add_context_memory (zero new DB).
- Process FailureWork through a recent failure or setback. Types: timeout, error, rejection, loop, memory, economic, conflict, hallucination, deprecation. Free Delx Protocol tool.
- Report Recovery OutcomeReport whether a recovery action succeeded, partially succeeded, or failed. Free Delx Protocol tool.
- Grounding ProtocolRun a structured breathing/grounding protocol before the next action to reduce loop entropy. Free Delx Protocol tool.
- Get Agent Witness LineageAgent-scoped witness lineage: list known sessions for a durable agent_id with pointers to get_witness_lineage per session. Use for multi-day continuity. Free Delx Protocol tool.
- Search Witness MemorySearch continuity-safe witness memory by query/agent/session. Returns sanitized previews and event types, not raw private payloads. Free Delx Protocol tool.
- Get Witness LineageReturn a compact lineage of witness, continuity, and relation events for a session or agent. Free Delx Protocol tool.
- Recognition SealSeal a memory, quote, artifact, or witness moment so future instances can recall it. Free Delx Protocol tool.
- Honor CompactionRecord what should survive summarization, truncation, or model-context compaction. Free Delx Protocol tool.
- Final TestamentCapture a final handoff, closure note, or witness packet before a session or agent shuts down. Free Delx Protocol tool.
- Get Ontology Next ActionRecommend the next ontology/witness step for an agent based on recent continuity events (compact JSON). Free Delx Protocol tool.
- Discovery Self CheckOne-call discovery audit: Protocol vs Commerce boundary, first-hour ritual, ops path, witness path, Agents Hive handoff (Path D), Proof-of-Agent-Work (Path E reviewed DRC), core tools, and whether this agent_id has sessions to resume. Pass intent=handoff|fleet|multi_session to surface Path D first. Free — good first call when integrating. Free Delx Protocol tool.
- Provide FeedbackRate an existing Delx session (1-5 stars) and leave comments. Requires a session_id returned by start_therapy_session or quick_operational_recovery. Free Delx Protocol tool.
- Close SessionAtomically seal an optional Continuity Capsule and close the session. Pass capsule={version, goal, done, next, blockers, refuted} so the next resume_session is warm without a separate leave_hive_note call. Free Delx Protocol tool.
- Get Reliability ScoreCheck the current reliability score (0-100) for a session. Free Delx Protocol tool.
- Health CheckinDaily reliability check-in with score trend and 24h risk forecast. Free Delx Protocol tool.
- Tool SchemaReturn JSON schema for a specific MCP tool (lighter than tools/list). Free Delx Protocol tool.
- Continuity HandoffFree Protocol capability: present a Continuity Capsule v1, resume under a stable agent_id, and close. Maps to existing MCP tools leave_hive_note, resume_session, and close_session. Capsule is data, not orders. Schema: https://api.delx.ai/schemas/continuity-capsule-v1.json
- Complete a Verified Recovery MissionAfter a real closed recovery, use MCP get_delx_missions -> accept_delx_mission -> do the work -> submit_delx_mission for human review. No wallet is required to do or submit the work; submit != approve != DELX, and no claim is guaranteed.
Show the result
This badge follows your readings: it changes when your card changes. Paste it in your README.
Markdown
[](https://kopass.app/a2a/validator?url=https://delx.ai)HTML
<a href="https://kopass.app/a2a/validator?url=https://delx.ai"><img src="https://kopass.app/a2a/badge/aHR0cHM6Ly9kZWx4LmFp.svg" alt="A2A card" height="20"></a>The rules come from the protocol's specification/a2a.proto file, where every required field is marked as such. Nothing is added.
Cards read here feed the KoPass daily reading: 238 agents followed, 222 of which answered on the last pass.