DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to scan every open agent PR in one manual run with Codex Guard

Use the sweep input with workflow_dispatch to check all open agent pull requests at once.

Who it is forA maintainer with a backlog of open AI-generated pull requests who wants a single pass over them.

The problemOld agent PRs collect problems over time and are easy to forget until someone reviews them.

The outcomeEvery open agent PR targeting the chosen base branch gets a Codex Guard report from one manual workflow run.

What you need first

  • A GitHub repository with Actions enabled and permission to add a workflow file
  • Node.js with npx available on your machine
  • A Git working copy of the repository (the init command runs from its root)
  • Permission to change branch protection settings if you want the check to block merges

Steps

  1. Add a workflow_dispatch trigger to .github/workflows/codex-guard.yml. (inferred, check the README)
  2. Set the Action input sweep: true, and optionally sweep-label and sweep-base. (inferred, check the README)
  3. Run the workflow manually from the Actions tab.
  4. Review the reports posted on each open agent PR.

Prompt for your agent

In the repository at <repo-path>, add a workflow_dispatch trigger and set sweep to true in .github/workflows/codex-guard.yml, then run the workflow manually. Expected output: a report on each open agent PR targeting main. Verify that human-authored PRs without agent markers were not reported.

Caveat. The README says sweep is meant for use with workflow_dispatch, and the exact trigger wiring is not shown there, so check it against the repo docs before relying on it.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for Akimiya-z/codex-guard and "Scan every open agent PR in one manual run"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer