opencode-companion
OpenCode Companion
OpenCode is a headless coding agent runtime. This skill lets you launch coding sessions, continue existing sessions, attach/wait for results, manage the serve process, and forward outputs through a single companion script.
Set the companion script path from this skill path:
SCRIPT="${SKILL_ROOT}/scripts/opencode-companion.mjs"
${SKILL_ROOT} is the path to this opencode-companion skill directory. Set it from the loaded skill path; do not prepend another install root.
Typical workflows
Host-background note
Several patterns below say "run this in the host agent's background mode." That phrase has a concrete mapping per host:
- Claude Code — call the
Bashtool withrun_in_background: true. The shell stays alive until OpenCode exits; Claude Code emits a task-completion notification with anoutput-filepath. Read that file to recover stdout (Session ID, status, etc.).
More from atomlink-ye/my-claude-plugins
paseo-companion
Paseo CLI companion. Load whenever the user mentions paseo, paseo agents, paseo run/send/wait/logs/attach/ls, agent IDs, sending follow-ups to a running agent, loops, schedules, terminals, worktrees, chat, permits, daemon operations, or host/port targeting.
12google-workspace
Read, create, and edit Google Workspace documents using the `gws` CLI. Use this skill whenever the user mentions Google Docs, shares a docs.google.com URL, references a Google Doc ID, or wants to read/write/create Google documents. Also trigger on 'GDoc', 'gdoc', 'Google Doc', 'gws docs', or any Google Workspace document operation. Will expand to cover Drive, Sheets, Gmail, Calendar, and other GWS services.
12daytona-companion
Daytona sandbox companion. Load for sandbox up/status/push/exec/pull/down/preview/smoke-test requests, adopting existing sandboxes, artifact and git-sync workflows, and sandbox environment variables or secrets.
12debug-workflow
Unified debug workflow skill for real-world issue reproduction, especially browser/UI/Web3 problems that need Playwright, shared Chrome/CDP, or agent-wallet. Use this whenever the user wants to confirm whether a workflow can reproduce real issues from walkthrough docs, issue lists, QA notes, or live bug reports. Start with the debug index, route to the right lane, and prefer deterministic local reproduction over fragile preview environments.
11task-iteration
Orchestrate end-to-end feature implementation from an exec-plan document. Use this whenever the user wants a structured Plan → Generate → Evaluate loop for a feature. It keeps planning and acceptance in Claude, pushes bounded coding/test execution to OpenCode companion sessions, reuses warm sessions across fix rounds, and gates completion on independent evaluation plus an advisory review.
11mcp-skill
On-demand MCP capability invocation via MCPorter. Use when the task needs browser automation (Playwright), documentation lookup (Context7), repository reading (zread), web search (web-search-prime), remote URL reading (web-reader), or any other MCP server. Use whenever you would otherwise want a persistent MCP server but the runtime is configured with no global MCP servers, so each MCP call must go through MCPorter.
11