Inspecting Codex Request Payloads Reveals 9,400 Token Overhead per Prompt

01Payload Decomposition and Initial Baseline

Capturing raw JSON HTTP requests from Codex CLI 0.145.0 reveals significant prompt wrapping. A basic 16-character user input (Reply with pong.) produces a raw request body of 42,980 bytes. When encoded using o200k_base, the payload estimates at approximately 9,435 tokens. The wrapped prompt accounts for roughly 25 tokens (~0.3% of the request payload), while system framing, permissions, context metadata, and bundled tools make up the remaining 99.7%.

02Instruction Chaining across AGENTS.md Files

Codex builds instruction chains by scanning upward from the working directory to the repository root:

• Starting in a child directory automatically aggregates AGENTS.md from the root down to that child folder.
• Executing file listing commands like ls child from the root does not trigger automatic loading of child/AGENTS.md into the instruction chain.
• Synthetic markers demonstrate that instruction text is passed verbatim in subsequent requests, directly impacting the prompt baseline.

03Output Truncation and History Compaction

Command execution output is appended directly into execution history. While a 10,000-line log is pruned to head-and-tail samples, payload size still spikes from ~9,584 tokens to 25,835 tokens. Compaction triggers when approaching configured limits (e.g., a 12,000 token threshold), executing a dedicated summary request (68,375 bytes / ~21,408 tokens) before rebuilding conversation history around retained messages.