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.
The hard rule: no API key, token, password, cookie, OAuth secret or account identifier ever enters the repository, its history, releases, issues or CI logs. Keys are read only at runtime, templates use ${ENV_VAR} placeholders, and gitleaks and the privacy scan run before every push and in CI over the full history.
When you need it
AI agents read and write many files quickly, so a single pasted key can spread into commits, briefs and logs before anyone notices.
How it works
Keys come only from environment variables or the OS keychain, through one documented lookup; a missing key leaves the feature off with unused(no key).
Templates and docs use placeholders such as ${TYPESAFE_API_KEY}, never values.
oah init adds local secret files to .gitignore; the opt-in pre-push hook scans pushed commits; oah land refuses without a gitleaks scan.
In oah's own repository, gitleaks and the privacy scan run before every push and in CI on every pull request and push, over the full history; any finding fails the build.
Example
The privacy scan oah's contributors run before every push; it must print `PRIVACY_SCAN_CLEAN`.
python3 tools/privacy_scan.py --gitleaks require
Requirements
gitleaks for scans and for landing.
Limits and recovery
A key that reached a commit, a push or a log is exposed even if you delete it a minute later: rotate it first.
The CI starter's secret scan prints no finding context and writes no report, so you see the failure, not the value.
Never put a secret in a CI-exception reason; the docs ask for a non-secret reason.