{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreibyni44pfsynztjetrxqnsvf2rcb56krp7oq2vuxkpa53gw3mpwby",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmfgvefpzgo2"
},
"path": "/t/how-are-you-managing-the-use-of-explicitly-spawned-subagents/1381187#post_4",
"publishedAt": "2026-05-21T21:35:48.000Z",
"site": "https://community.openai.com",
"tags": [
"Sub Agent Limit Bug - codex plugin in vs code",
"Codex"
],
"textContent": "I agree, this is a pain point that needs to be managed on top of Codex because subagents can currently get lost.\n\nWe recently had a topic about this where it was not even clear whether we were looking at a bug or something else entirely:\n\nSub Agent Limit Bug - codex plugin in vs code Codex\n\n> At some point the session responded with a subagent limit reduction. Could only spawn 2 instead of the normal 6 subagents limit. I’ve waited for ~12 hours and then tried again. Still only 2 subagents. Then I restarted vs code and opened a new session and back to 6.\n\nWith Codex I prefer to spawn subagents for distinct, one-shot tasks only and then have the orchestrator monitor the status until the agent is done and can be despawned.",
"title": "How are you managing the use of explicitly spawned subagents?"
}