oah helps you build an AI development workflow that fits you and keeps changing as AI improves. It is a working reference and a guide you can adapt.
A useful result needs more than generated code: the scope must be clear, the changes checked, and decisions kept for the next session. oah connects those steps so one request can carry through the work with a record of what happened.
002 / Why it keeps changing
Older rules and skills can hold a newer model back or make its results worse. Defaults should be easy to understand and change; a rule that gets in your way is a design problem to fix.
Keep the parts that help, remove what no longer helps, and revise the workflow as your tools improve. You can start with the full setup or take only the impact map, wiki, leases, evidence gates or review loop that your project needs.
003 / Why Claude builds and Codex reviews
This split comes from the author's own experience, not a measured comparison: Claude fills in details a beginner might miss in a first version; Codex checks and corrects within a fixed scope.
The current commands run Claude Code and Codex CLI. The ideas can also be adapted to another tool or harness, with one AI or several. Give each stage to the AI that suits your work.
004 / From one request to a checked change
Describe the result you want in plain language. The AI records the goal and scope, checks what the change touches, reserves its paths and chooses the tools for the task. Claude builds; Codex reviews, corrects and reviews again.
Gates record the checks and their results. The project wiki keeps the decisions and reasons beside the code. In v0.3.0, optional TypeSafe Jev can judge difficulty for model selection; rules remain the fallback when it is unavailable or uncertain.
005 / The decisions stay with you
You ask, answer when the AI needs a decision, and confirm before the change lands. If the same problem repeats or the work reaches a design choice, the loop stops to ask you.
Ask “Is the review done?” or “Did all the gates pass?” and inspect the evidence. The final confirmation belongs to you; writing code, checking it and approving its landing are separate steps.
006 / Free, open source, yours to adapt
oah is free, open-source software under the MIT license. Read the source, change it and bring the useful pieces into your own workflow. Your AI services and any optional services use their own accounts and billing.
The current v0.3.0 release supports macOS and native Windows, and expects familiarity with git and pull requests. Install it, run oah init in your project, then try the small hello-oah example. The installation and documentation sections explain each step.
New in v0.3.0: a review never runs below the floor for its risk, whatever a flag, packet, profile or judge says. The floor is medium, or high when a path in the review's scope is risky or its kind needs it. It is scored again from the scope, and a refusal spends no review round or attempt.
When you need it
If a cheap profile, a flag or a judge could lower the reviewer, the one stage that guards everything else could quietly get weaker.
How it works
The floor is recomputed from the review's scope, so no flag, packet axis, profile or judge answer can lower it.
It is a mark on the fixed score scale, so a narrow allowed_models cannot lower it either.
A review whose tier, model or effort is below the floor stops with OAH_MODEL_BELOW_FLOOR, spending no round or attempt.
A review receipt records the family, floor, profile, source of the model and the scores used.
Requirements
Requires v0.3.0 or later.
Limits and recovery
A model you named that has no score runs with OAH_MODEL_FLOOR_UNCHECKED, and the receipt says the floor was not checked.
When no allowed model reaches the floor, the review stops and the message names allowed_models; use the tier it names, or change the pin, pool, quality_order or allowed_models.
For example, --tier low on a review is refused; use the tier the message names.