# AI use cases for Procoder (azrtydxb/procoder)

Repo: [azrtydxb/procoder](https://github.com/azrtydxb/procoder) | Use cases: 4 | Page: https://dedupedai.com/use-cases/azrtydxb-procoder/

Procoder is a Go binary and agent plugin that adds a commit gate, quality controllers, and a lessons loop to AI coding agents.

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

- Gate agent commits so bad changes never land: https://dedupedai.com/use-cases/azrtydxb-procoder/gate-agent-commits-before-they-land/
- Stop an agent from closing unfinished tasks: https://dedupedai.com/use-cases/azrtydxb-procoder/stop-agent-closing-unfinished-todos/
- Run release checks before a version tag: https://dedupedai.com/use-cases/azrtydxb-procoder/run-release-checks-before-tagging/
- Audit an existing codebase with a triaged scorecard: https://dedupedai.com/use-cases/azrtydxb-procoder/audit-existing-codebase-with-scorecard/

## How to gate agent commits so bad changes never land with Procoder

Repo: [azrtydxb/procoder](https://github.com/azrtydxb/procoder) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Run the commit gate on agent output to catch formatting, conflict markers, junk files, and secrets.

**Who it is for:** A developer whose AI agent writes code in a git repository and who wants a check before each commit.

**The problem:** Agents often leave unformatted files, conflict markers, staged junk, or AI attribution lines, and say the work is done anyway.

**The outcome:** Each run lists the blocking findings and the fixed formatting, so the agent corrects the change before committing.

### Steps

1. Run `/plugin marketplace add azrtydxb/procoder`
2. Run `/plugin install procoder`
3. Run `/procoder:init` to install the tools this repository needs
4. Run `procoder check` and read the blocking findings
5. Run `procoder format "<file>"` on any unformatted file, then run `procoder check` again (inferred, check the README)

### Prompt to paste into your agent

```text
In the azrtydxb/procoder-enabled repository at <repo-path>, run `procoder check` after your changes. Report the count of blocking findings and fix each one before you commit. Verify that the final run shows zero blocking findings.
```

### Caveat

The full check set applies only to repositories that have adopted Procoder, so in someone else's repository only the universal checks run.

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/azrtydxb-procoder/gate-agent-commits-before-they-land/

## How to stop an agent from closing unfinished tasks with Procoder

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

Make todo close refuse until criteria are checked, evidence is recorded, and the gate is clean.

**Who it is for:** A developer using an agent for standalone tasks who keeps finding work marked done that was not finished.

**The problem:** An agent reports a task as complete without checking the acceptance criteria or running verification.

**The outcome:** A task closes only after every acceptance criterion is checked, evidence is recorded, and the gate is clean.

### Steps

1. Run `/plugin install procoder` in the repository if it is not installed yet
2. Create a todo item with its acceptance criteria using the Procoder todo command (inferred, check the README)
3. Run `procoder check` and fix every blocking finding
4. Run `procoder todo close` on the item and read any refusal (inferred, check the README)
5. Record the missing evidence or unchecked criteria the refusal names, then close again

### Prompt to paste into your agent

```text
In the procoder-enabled repository at <repo-path>, close the todo item <item-id> only after its acceptance criteria are checked and the gate is clean. Report the refusal text if the close is refused. Verify that the item shows as closed only when the gate result is clean.
```

### Caveat

The README names the todo close behavior but does not show the exact todo subcommand syntax, so the steps marked inferred need checking against the command reference.

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/azrtydxb-procoder/stop-agent-closing-unfinished-todos/

## How to run release checks before a version tag with Procoder

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

Use Procoder release to catch version drift, a missing changelog entry, and a red test suite before tagging.

**Who it is for:** A maintainer preparing a release of a repository that an agent has been editing.

**The problem:** A tag gets cut with mismatched version numbers, no changelog entry, a dirty tree, or a failing suite.

**The outcome:** All release failures arrive in one list, and on success the git tag command is printed for you to run.

### Steps

1. Run `procoder test` and confirm the suite shows PASS, not NOT run
2. Run `procoder check` and resolve every blocking finding
3. Run `procoder release` and read the full failure list
4. Fix each listed failure, such as version files or the changelog entry
5. Run the `git tag` command that `procoder release` prints, yourself

### Prompt to paste into your agent

```text
In the procoder-enabled repository at <repo-path>, run `procoder release` and fix every listed failure without tagging. Report the final list. Verify that the tag command is printed only when all checks pass and that you run it yourself.
```

### Caveat

Procoder tags nothing itself, and the suite check reports NOT run as a failure, so an unrunnable test suite blocks the release rather than passing 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/azrtydxb-procoder/run-release-checks-before-tagging/

## How to audit an existing codebase with a triaged scorecard with Procoder

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

Onboard a legacy repository and get a triaged scorecard of its quality before an agent edits it.

**Who it is for:** An engineer taking over an existing codebase who wants to know its quality before handing work to an agent.

**The problem:** An unfamiliar repository has unknown gaps in security, lint, documentation, CI, and dead code, and no ordered list of what to fix first.

**The outcome:** A triaged scorecard across Procoder's domains, which the engineer can use to decide what the agent should fix first.

### Steps

1. Install the plugin with `/plugin marketplace add azrtydxb/procoder` and `/plugin install procoder`
2. Run `procoder audit` in the repository root (inferred, check the README)
3. Read the scorecard and sort findings by the triage it shows
4. Run `procoder check` to see the blocking items in the current tree
5. Give the agent one domain from the scorecard at a time to fix

### Prompt to paste into your agent

```text
Run the procoder audit command in the repository at <repo-path> and summarize the triaged scorecard. Pick the highest-priority blocking item and propose a fix without editing files yet. Verify that the audit output reports which mode it ran in.
```

### Caveat

The README says the audit command onboards existing codebases but does not show its exact syntax, so the audit step is inferred and should be checked against the command reference.

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/azrtydxb-procoder/audit-existing-codebase-with-scorecard/
