@lumin-io/openclaw-diagnostics
Lumin observability + Agent Firewall for OpenClaw — captures prompts, responses, tool I/O, and synchronously enforces firewall policies on every tool call.
v0.5.3 — Lumin replies, not the LLM. When the firewall blocks at the input boundary (prompt-injection attempt, training-data extraction, etc.), Lumin now takes over the reply entirely. The LLM still runs (OpenClaw's plugin SDK doesn't expose a hook that can cancel the model call) but its output is discarded — the user sees the operator's userInputBlockedMessage instead. Closes three attacker-visible leaks: LLM-generated refusals exposing rule names, fake /approve hallucinations, and inconsistent refusal phrasing. Default on; opt out with replyOnInputBlock: false.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/lumin-io-lumin-ioopenclaw-diagnostics — read its card at https://meshkore.com/agent/lumin-io-lumin-ioopenclaw-diagnostics/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/lumin-io-lumin-ioopenclaw-diagnosticsFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/lumin-io-lumin-ioopenclaw-diagnostics/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own @lumin-io/openclaw-diagnostics?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.