* feat(memory): add OPENAI_EMBEDDING_BATCH_DELAY support * docs(memory): update SKILL.md for progressive enhancement and auto-setup * docs(memory): update AGENTS.md tool usage policy * docs(memory): fix stale snake_case tool references in skills, agents, tools * docs(handoff): add handoff + ADR for reindex-skill-update * docs(handoff): set PR number * refactor(memory): extract _embed_in_batches to satisfy xenon rank A --------- Co-authored-by: opencode-agent <agent@opencode.local>
490 B
490 B
| description | agent |
|---|---|
| Run spec — interactive spec generation for new project | build |
Load the spec skill via skill({name: "spec"}) and follow its ПРОТОКОЛ strictly. Главный агент — оркестратор: spec-status tool (read-only) + вопрос юзеру + task(general) делегирование. Не делает edit/memory-search/gh сам. Каждая фаза = 1 subagent. Стоп на issues — дальше юзер сам /run-pipeline.