coordinate-external-ag…
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Design, implement, test, and package an ACP agent/server. Use for protocol negotiation, sessions, streaming updates, tool rendering, permissions, authentication, SDK choice, and registry submission.
$ npx -y skills add gaelic-ghost/socket --skill build-acp-agent --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/build-acp-agentContext preview
The summary Claude sees to decide when to auto-load this skill.
Design, implement, test, and package an ACP agent/server. Use for protocol negotiation, sessions, streaming updates, tool rendering, permissions, authentication, SDK choice, and registry submission.
name: build-acp-agent
description: Design, implement, test, and package an ACP agent/server. Use for protocol negotiation, sessions, streaming updates, tool rendering, permissions, authentication, SDK choice, and registry submission.
metadata:
hermes:
category: agent-portability
tags: [acp, json-rpc, sdk, registry, agent-development]Build the agent process that an ACP client launches. Do not build an editor plug-in or MCP server when the requirement is an editor-native coding agent. Read `references/acp-implementation-map.md` before selecting an SDK or registry distribution.
1. Define concrete client targets and the user-visible behavior they require. 2. Use ACP v1, the current latest protocol, and an official SDK when its language and runtime fit. Treat v2 and non-completed RFDs as experimental; do not ship them as the portable baseline. Use raw JSON-RPC only when an SDK cannot support a required platform or feature. 3. Implement initialization first:
4. Implement the required session baseline: new, prompt, cancel, and update. 5. Add optional load, resume, fork, list, close, modes, configuration, plans, slash commands, rich prompt content, or MCP transports only with matching capability declarations and tests. Keep draft `session/delete`, logout, elicitation, additional directories, and remote transports behind explicit experimental flags and interoperability tests. 6. Render tool calls, diffs, terminals, plans, and streamed content in the ACP structures the target clients understand. 7. Route dangerous operations through permission requests and fail closed when approval transport fails or times out. 8. Keep stdout exclusively for ACP JSON-RPC. Send logs and diagnostics to stderr without leaking credentials or prompt content unnecessarily. 9. Bind every session to its client-provided cwd and any negotiated additional roots. Isolate cancellation, model choice, history, and mutable state by session. 10. Test initialization, authentication, session lifecycle, streaming, cancellation, permissions, invalid messages, process shutdown, and each advertised optional capability against representative clients.
as three separate states.
ACP process directly and reproducibly.
package.
availability until the live registry feed contains the entry.
registry requires authentication discovery.
merely to satisfy a distribution shape.
verify the canonical registry path after publication.
permissions. Keep Xcode tool behavior separate from protocol conformance.
Hermes adapter's session, approval, cwd, and provider behavior.
numbers; use negotiated ACP protocol version and capabilities.
or test fixtures.
Report client targets, SDK and protocol version, required and optional methods, capability matrix, auth flow, session/state model, permission behavior, distribution source, registry state, tests, and client-specific limitations.
Stuff for Agents on macOS Promo audio: Socket Codex Marketplace Promo
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Assign worktree, branch, write, validation, integration, and cleanup ownership before parallel repository work. Use when a worker will inspect or modify…
Design framework-neutral agent and automation workflows before implementation. Use when choosing between Codex app automations, codex exec, Codex subagents,…
Design evaluation workflows for agent, skill, prompt, and automation behavior before implementation. Use when choosing eval cases, graders, thresholds,…
Design safe n8n workflows with deterministic routing, credentials, idempotency, recovery, local-model checks, drafts, and exact approval gates.
Coordinate bounded worker tasks with a launch envelope, report-back, escalation, and synthesis contract. Use before spawning, resuming, steering, cancelling,…