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.
oah ci init writes .github/workflows/oah-ci.yml after showing it in full and asking. It runs your tests on the operating systems you choose and a pinned gitleaks secret scan on every push and pull request, with every action pinned to a full commit SHA, read-only permissions and no secrets. Making the checks required is a GitHub setting you add yourself.
When you need it
Without CI, or with CI on one OS only, a change that breaks tests elsewhere or leaks a key reaches the default branch unnoticed.
How it works
Run oah ci init; it looks for your test command (pytest, unittest, npm test, go test or cargo test) and asks whether to use it.
It prints the whole workflow and asks Write .github/workflows/oah-ci.yml? [y/N]; nothing is written unless you answer y.
Two jobs: test once per chosen OS (macos-latest, windows-latest, ubuntu-latest), and secret scan, which checks the gitleaks download by its SHA-256 fingerprint and scans the whole history with --redact --no-banner.
Commit and push; read results in the Actions tab or at the bottom of the pull request.
To block merges until checks pass, add a branch ruleset on GitHub requiring secret scan and one test (…) per OS.
Example
Keep your choices in `.oah/config.toml`; a command-line flag wins (from CI starter).
[ci]
os = ["macos", "windows"]
test_command = "make test"
Requirements
A GitHub repository. Rulesets work in public repositories on every plan, and in private ones with GitHub Pro, Team or Enterprise Cloud.
npm ci needs a committed package-lock.json.
Limits and recovery
oah never changes repository settings; required checks are yours to add.
An existing workflow is never replaced silently: --yes alone refuses, and only --force --yes replaces it without asking.
If no test command matches, the workflow gets a failing **Run tests (edit me)** step for you to replace.
If secret scan fails, rotate the key with its issuer first; deleting it in a new commit leaves it in history.