Tag: workflow · Developer ========================= Page address: https://yotamfromm.dev/developer/tags/workflow/ Updated: 2026-10-22 Markdown version: https://yotamfromm.dev/developer/tags/workflow.md Site map for agents: https://yotamfromm.dev/llms.txt The items with the tag, newest first. - Claude writes, Codex reviews (https://yotamfromm.dev/developer/blog/claude-writes-codex-reviews.md): A review from a different model family caught bugs my passing tests missed, cost 20 extra minutes on four real bugs where it changed nothing, and once let three HIGH defects ship because I read repeated findings as a pass. This is how the review is wired, what the trials showed, and how to set one up. · Plain text (https://yotamfromm.dev/developer/blog/claude-writes-codex-reviews.txt) · lang: en - Caps, gates and routing belong in code (https://yotamfromm.dev/developer/blog/deterministic-gates.md): Every rule I left to an agent's judgment was skipped sooner or later: a stamp-at-the-end reminder that was broken in every one of its 32 failures, a 650,000-token ceiling a run overspent to 1,444,564, a judge that opened 20 of 48 screenshots. This is how I moved those rules into scripts, hooks and exit codes, how I prove each gate can fail, and how you can write one. · Plain text (https://yotamfromm.dev/developer/blog/deterministic-gates.txt) · lang: en - Four tasks, three setups, hidden tests: plain Opus matched my /work process (https://yotamfromm.dev/developer/blog/hidden-tests-trial.md): On four real backlog items scored by tests the agents could not see, plain Opus passed every hidden test my tuned /work process passed, in 7 minutes and $2.46 against 53 minutes and $8.92, in notional API dollars. This is how I set up the trial so the agents could not game it, what it showed, and why I retired /work. · Plain text (https://yotamfromm.dev/developer/blog/hidden-tests-trial.txt) · lang: en The full page: https://yotamfromm.dev/developer/tags/workflow/