opencode-api-control-skill
von malek262
Web & Frontend DevelopmentKurzbeschreibung
A powerful skill to control Open Code CLI via a local web server API.
Beschreibung
Was dieser Skill macht
Controls the OpenCode CLI through its local HTTP API using a set of shell scripts. Acts as an orchestrator that sends coding tasks to OpenCode, manages sessions and providers, and monitors progress without reading or modifying generated files directly. State is persisted locally so workflows can resume across runs.
Keeps orchestration separate from execution so the agent never interrupts OpenCode mid-task by poking at files, reducing errors from partial reads or conflicting writes.
Wann du ihn einsetzt
- Delegating a new React app build to OpenCode and tracking its progress
- Switching between AI providers (Anthropic, Gemini) for different coding tasks
- Running multi-phase dev workflows: plan with one session, implement in another
- Resuming a paused coding session by loading saved project state
- Monitoring long-running code generation with real-time event streaming
Beispiel-Workflow
User asks: Create a React dashboard app using Claude Sonnet
- 1
Run update_providers.sh to refresh the connected providers cache
- 2
Run select_provider.sh with 'claude' and 'sonnet' to get provider and model IDs
- 3
Create the project directory and a new session with create_session.sh
- 4
Send the task via send_message.sh using the selected provider and model
- 5
Run monitor_session.sh to stream progress, then get_diff.sh to summarize changes
Diff summary listing added files such as src/App.tsx (+120/-0) and src/components/Dashboard.tsx (+89/-0), reported to the user without reading file contents
Voraussetzungen
- OpenCode CLI installed and server running on port 4099
Installation
clawhub install malek262/opencode-api-control-skillFühre den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.