8 pages tagged

#codex

agent-legibility

Designing systems for the agent's eye, not the human's; logs, metrics, code all agent-readable.

architectural-invariants

Strict layering enforced by custom linters with embedded fix instructions.

codebase-as-system-of-record

"If the agent can't find it in the repo, it doesn't exist"; versioned artifacts as truth.

entropy-and-garbage-collection

Golden principles + scheduled cleanup tasks; debt paid down in small installments.

ralph-wiggum-loop

Agent self-review pattern: loop until every reviewer + verifier is satisfied; Codex's PR cycle.

2026-04-27-codex-context-compaction-investigation

Kangwook Lee's prompt-injection probe extracting Codex's hidden compaction & handoff prompts.

2026-04-27-harness-engineering-codex-agent-first

Ryan Lopopolo / OpenAI Codex's "no manual code" 5-month, 1M-LoC, 1500-PR experiment.

2026-07-12-codex-windows-sandbox-engineering

OpenAI's Codex Windows sandbox: rejected primitives → unelevated prototype → elevated design.