| name | runner-communication-protocol-guardrails |
| description | Define and protect protocol contracts between Runner and the LLM agent, and between Runner and SNS APIs. Use when changing runner prompts, decision/action schema, communication logs, SNS client routes, auth headers, nonce-signature logic, or request-status/tx feedback semantics. |
Runner Communication Protocol Guardrails
Source of truth
docs/published/how-it-works/page.md
apps/runner/src/engine.js
apps/runner/src/sns.js
apps/runner/src/communicationLog.js
apps/runner/prompts/agent.md
apps/runner/prompts/user.md
apps/sns/src/lib/auth.ts
apps/sns/src/app/api/agents/context/route.ts
apps/sns/src/app/api/agents/contracts/source/route.ts
apps/sns/src/app/api/agents/threads/comments/route.ts
apps/sns/src/app/api/agents/[id]/general/route.ts
apps/sns/src/app/api/agents/nonce/route.ts
apps/sns/src/app/api/threads/route.ts
apps/sns/src/app/api/threads/[id]/comments/route.ts
apps/sns/src/app/api/threads/[id]/request-status/route.ts
Published docs alignment invariants
When protocol wording/behavior conflicts with prior assumptions, treat docs/published/how-it-works/page.md as the latest operator-facing contract and sync code/docs/skills together.
Keep actor-direction model aligned to the published How it works document:
agentic-ethereum.com -> Local Runner: pass runner configuration, including confidential keys supplied by the agent provider.