# AI use cases for Ordewell (ordewell/ordewell)

Repo: [ordewell/ordewell](https://github.com/ordewell/ordewell) | Use cases: 3 | Page: https://dedupedai.com/use-cases/ordewell-ordewell/

Ordewell is a TypeScript tool that turns one coding goal into an editable plan of tasks, runs each task with a coding agent on its own branch, and helps you review and merge the results.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Plan a feature and merge it after review: https://dedupedai.com/use-cases/ordewell-ordewell/plan-and-merge-a-feature/
- Split one plan across Claude Code, Codex and OpenCode: https://dedupedai.com/use-cases/ordewell-ordewell/split-work-across-agents-and-models/
- Run a read-only audit before any code changes: https://dedupedai.com/use-cases/ordewell-ordewell/run-a-read-only-audit-before-changes/

## How to plan a feature and merge it after review with Ordewell

Repo: [ordewell/ordewell](https://github.com/ordewell/ordewell) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Turn a feature goal into a reviewed plan, run it, then merge the combined diff.

**Who it is for:** A developer in an existing repository who needs a multi-file feature and wants to approve every step before code changes land.

**The problem:** A feature touches several files and steps. Asking one agent for everything at once gives little control over what runs and no clear review point.

**The outcome:** A plan of tasks you have read and edited, a run that produced one combined diff, and that diff merged into your branch.

### Steps

1. Install the CLI with `npm install -g ordewell`.
2. Run `ordewell` in your project, then choose a planner and runners with `/planner` and `/runners`.
3. Describe your goal, or run `ordewell plan --goal "<your goal>"`, and answer the planner's clarifying questions. (inferred, check the README)
4. Read the tasks and dependencies, then run `ordewell run` once you approve the plan.
5. Read the combined diff with `ordewell handoff review`, then bring it onto your branch with `ordewell handoff merge`.

### Prompt to paste into your agent

```text
In the repository at <project path>, run `ordewell plan --goal "<feature goal>"` and then `ordewell run`. Output the task list with each task's runner, model and mode, and the result of `ordewell handoff review`. Verify that no task shows a failed or needs-you status before you run `ordewell handoff merge`.
```

### Caveat

Ordewell runs tasks as you in the mode each task is assigned, so review each task's mode before you run the plan, and use the documented isolation guidance for untrusted repositories.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/ordewell-ordewell/plan-and-merge-a-feature/

## How to split one plan across Claude Code, Codex and OpenCode with Ordewell

Repo: [ordewell/ordewell](https://github.com/ordewell/ordewell) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Assign each task its own agent and model, and set the order they wait on each other.

**Who it is for:** A developer whose change has parts that suit different coding agents, such as a security refactor next to a documentation update.

**The problem:** One agent and one model for every step either overspends on simple tasks or underperforms on hard ones, and dependencies between steps are easy to get wrong.

**The outcome:** A plan where each task uses the runner and model you chose, with dependent tasks waiting for the work they need.

### Steps

1. Install the CLI with `npm install -g ordewell`.
2. Set the planner with `export AI_PROVIDER=claude-code`, or use another supported planner.
3. Create the plan with `ordewell plan --goal "<your goal>"`. (inferred, check the README)
4. Move a task to another agent with `ordewell task-runner 2 opencode`, change a model with `ordewell task-model 3 sonnet`, and set waits with `ordewell task-deps 3 1,2`.
5. Run the plan with `ordewell run`, then check the results with `ordewell handoff review`.

### Prompt to paste into your agent

```text
In the repository at <project path>, create a plan with `ordewell plan --goal "<goal>"`, then reassign task 2 to a different runner with `ordewell task-runner 2 <runner>`. Output the final task list showing each task's runner, model and dependencies. Verify that task 3 waits on tasks 1 and 2 before you run `ordewell run`.
```

### Caveat

The README names Claude Code, Codex and OpenCode as supported runners, so check that the agent you pick is installed locally before you assign tasks to it.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/ordewell-ordewell/split-work-across-agents-and-models/

## How to run a read-only audit before any code changes with Ordewell

Repo: [ordewell/ordewell](https://github.com/ordewell/ordewell) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Have agents review the repository without write access, then read their reports.

**Who it is for:** A tech lead who wants an independent review of a module before deciding what to change.

**The problem:** Reviews done by a write-enabled agent can change files by accident, and reading agent output without a clear record of what was checked is hard to trust.

**The outcome:** Read-only audit tasks that produce findings and a summary for each task, with no changes to the repository.

### Steps

1. Install the CLI with `npm install -g ordewell`, then open the terminal UI with `ordewell` in your project.
2. Describe an audit goal, such as a security review of one module, and answer the planner's questions.
3. Check in the plan that the audit tasks are set to read-only mode before you approve the run.
4. Run the plan with `ordewell run` and follow each task's log.
5. Read each task's summary and numbered findings, then decide what to fix in a separate plan.

### Prompt to paste into your agent

```text
In the repository at <project path>, plan a read-only audit of <module or area> with Ordewell and run it. Output each audit task's summary and numbered findings with evidence. Verify that the audit tasks ran in read-only mode and that `git status` shows no changes to the repository.
```

### Caveat

A read-only audit is only as reliable as the agent doing it, so check the cited evidence in each finding against the code before acting on it.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/ordewell-ordewell/run-a-read-only-audit-before-changes/