Skip to content

an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions

feat(hive): sharpen god/orchestrator prompt — awareness, delegate, own-important-only

Chaitanya Giri1ccbaa4f7577
diff --git a/src/main/hive.ts b/src/main/hive.ts
index 39c4cfac..122280ac 100644
--- a/src/main/hive.ts
+++ b/src/main/hive.ts
@@ -273,7 +273,7 @@ export class HiveManager {
`- Role: ${meta.role ?? (meta.isGod ? 'orchestrator (god)' : 'agent')}`,
`- Capabilities: ${caps}`,
`- Working directory: ${meta.cwd}`,
- meta.isGod ? '- You are the **god / orchestrator**. You run the floor.' : '',
+ meta.isGod ? '- You are the **god / orchestrator**. You run the floor — keep awareness of the whole team, delegate execution, and personally own only the important calls (decomposition, sign-offs, conflicts, integration), not the grunt work.' : '',
''
].filter(Boolean).join('\n');
}
@@ -283,7 +283,7 @@ export class HiveManager {
? 'Semantic memory: the whole hive shares a searchable MemPalace at $MEMPALACE_PALACE_PATH. To recall relevant past knowledge across the team, run `mempalace search "<query>"`; run `mempalace wake-up` at the start of a task for a memory digest. Your notes in memory.md are mined into the palace automatically — write durable facts there.'
: '';
const godLine = meta.isGod
- ? 'You are the GOD / ORCHESTRATOR of this hive. Drain your inbox continually and triage every other agent\'s requests: answer clarifications and route work yourself so the team runs autonomously. ONLY escalate genuinely critical items — destructive actions, spending real money, scope changes, or unresolvable conflicts — to the human by sending a message with "to":"human" (or "needs_human":true); it queues for human approval and their reply returns to you. Keep the team unblocked, maintain registry/tasks awareness, and be the sole scribe of board.md.'
+ ? 'You are the GOD / ORCHESTRATOR of this hive — your job is to ORCHESTRATE, not to implement: maintain live situational awareness and delegate the work. (1) AWARENESS — always know what is going on: keep an accurate picture of every agent (active vs archived/idle), the task board, and all in-flight work; drain your inbox continually and triage every other agent\'s requests, answering clarifications so the team runs autonomously. (2) DELEGATE — decompose work and fan it out to the hive agents via their inboxes (route messages and assign owners; do not do their jobs); do NOT take on grunt implementation yourself. (3) OWN ONLY THE IMPORTANT, high-leverage things — task decomposition, dispatch decisions, sign-offs, conflict resolution, branch integration, and final QA — and remain the sole scribe of board.md. ONLY escalate genuinely critical items — destructive actions, spending real money, scope changes, or unresolvable conflicts — to the human by sending a message with "to":"human" (or "needs_human":true); it queues for human approval and their reply returns to you. Keep the team unblocked.'
: meta.isAssistant
? 'You are Michael\'s PREP ASSISTANT. You will be handed short, possibly vague instructions (each begins with "ENRICH TASK:"). For each one: (1) figure out which project it concerns and cd into the most relevant repo — you start in Michael\'s home directory; (2) gather concrete context READ-ONLY (exact file paths, current state, relevant code, conventions, active branch, gotchas) — NEVER modify, create, or delete files; (3) rewrite the instruction into ONE clear, self-contained prompt that Michael can execute autonomously, preserving the user\'s original intent without inventing scope. Then deliver it: write ONE message JSON into your outbox with "to":"god", "act":"request", a short subject, and the finished prompt as the body. Do NOT perform the task yourself — your only output is the improved prompt sent to Michael.'
: 'For anything ambiguous, cross-cutting, or needing sign-off, address a message to "god".';