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 land --check decides whether the exact reviewed head may land, printing one line each for lease, intent, review, gates, impact, required checks, fast-forward, secret scan and CI. oah land --merge runs every check again, asks you to confirm, and only then fast-forwards the remote default branch to exactly that head.
When you need it
Merging without a converged review, passing CI or a secret scan is easy to do by accident, and an agent should never push or merge on its own.
How it works
oah land --check --task T prints one line per check: lease, intent, review, gates, impact, required-checks, fast-forward, scan and ci.
gh reads HEAD's check runs and commit statuses; all latest results must be successful (check runs may also be neutral or skipped), with a result for every configured required check.
oah land --merge --task T reruns every check, asks you to confirm by typing y, and fast-forwards the remote default branch to exactly HEAD only if it still equals the commit just checked.
If someone else landed first, nothing is pushed: fetch, reassess and try again.
Missing gh, no results or a missing required check makes CI unverified, which blocks by default (OAH_LAND_CI_UNVERIFIED). --accept-unverified-ci "<reason>" on both commands records a per-head exception, and CI stays unverified, never a pass.
Example
Check, then land after confirming (worked example, step 9).
oah land --check --task hello-name
oah land --merge --task hello-name
Requirements
gitleaks for the scan; without it the scan line fails with OAH_LAND_SCAN_REQUIRED and nothing is pushed.
gh, signed in, for reading CI results.
A remote with a URL or an absolute path; landing refuses a relative path.
Limits and recovery
Failed CI (OAH_LAND_CI_FAILED) or pending or unreadable CI (OAH_LAND_CI_PENDING) blocks landing, and no exception can bypass them or any other failed check.
A commit after the converged review needs a new round (OAH_LAND_REVIEW_REQUIRED).
The [land] policy comes from the target branch's committed .oah/config.toml; loosening it in the task head refuses with OAH_LAND_POLICY_LOOSENED.