Codex Sub-Agents Quickly Drain Credits
ssh4net · x · 2026-07-10
A shared config.toml snippet for Codex's multiagentv2 includes:
- hidespawnagentmetadata = false
- toolnamespace = "agents"
The post points out a flaw in Codex's sub-agent orchestration: the spawnagent tool cannot specify the model or reasoning effort for sub-agents. Consequently, every time the main agent spawns a sub-agent, it launches another identical Sol Ultra instance, causing credits to drain rapidly.
Related event: Codex Sub-Agent Orchestration Flaw Drains Quota with Expensive Models(3 posts)→
More from coding & agent
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11
- 9-year backend dev: AI code isn't the problem, the rate of making a mess is — Sweaty-Landscape-561 · 2026-09-11
- RTK claims token savings, but our cost benchmarks disagree — michalwarda · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- Anthropic researcher: 99% of engineers now run swarms of 300+ self-improving agents — AlishaOutridge · 2026-09-11