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.
Released in v0.3.0: TypeSafe Jev judges difficulty from the task's Intent and Scope paths. When its confidence reaches the threshold, its tier runs, never below the floor. When Jev is off or has low confidence, the rule-based difficulty runs. A call is never blocked.
When you need it
Rules score the axes from the Scope alone, so a one-line concurrency fix can score low and a 20-file rename high.
How it works
Jev receives the four axes and a work text: the five parts of the accepted Intent (Problem, Desired outcome, Success conditions, Constraints and Non-goals), then the Scope paths, cut to 16,000 characters (about 4,000 tokens).
Before anything is sent, the privacy scanner's content rules read the text; if one flags a part, nothing is sent, the status is unused(secret), and OAH_RERANK_SECRET names the part, never the match.
When Jev's confidence is at or above [rerank] difficulty_min_confidence (0.6 unless you set a number from 0 to 1), its tier runs, raised to the floor tier when lower, and tier_source is jev.
Otherwise the rule tier runs and jev_status says why. --tier, or a plan tier you edited, leaves Jev out as unused(tier-given).
Run records and review receipts keep rule_tier, jev_tier, jev_confidence, jev_status, tier and tier_source.
Requirements
Requires v0.3.0 or later.
[rerank] enabled = true and your own TYPESAFE_API_KEY.
Limits and recovery
Jev never receives code, diffs, file contents, stored values, the brief or your key; a path is sent as a path, never its contents.
The first request in a project prints OAH_RERANK_SCOPE_WIDENED once; set enabled = false under [rerank] to stop every request.
A review's floor stays scored from its scope alone, so Jev can lower a review only down to that floor.
A thin Intent gives a thin judgement, and TypeSafe may charge for each request.
A difficulty_min_confidence outside 0 to 1 refuses with OAH_CONFIG_INVALID before anything is sent.