DOCUMENT OPS

Nightly sweep of all repo READMEs that files issues for broken examples

Each night, walks every repository in a GitHub org, runs the code examples in each README, and opens a labeled GitHub issue for any repo whose examples fail — one issue per repo.

CategoryDocument Ops
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNightly schedule
  • ActionList all active repos in the orgGitHubGitHub
  • ActionClone repo and extract README code blocksGitHubGitHub
  • ActionRun each example in a sandboxShell
  • LogicDid any example fail for this repo?
  • OutputOpen or update a labeled GitHub issueGitHubGitHub

What it does

Runs a fleet-wide drift audit while you sleep. It enumerates every repo in your GitHub org, executes the README's runnable code blocks against a fresh checkout, and files a tracked issue wherever an example no longer works. Healthy repos stay silent.

When to use it

Use it when you maintain many repos and can't watch each README by hand. Good for platform teams, OSS orgs, and internal tooling fleets where docs quietly rot after dependency bumps.

How it works

  1. 1A nightly schedule fires the sweep.
  2. 2The workflow lists all non-archived repositories in the GitHub org.
  3. 3For each repo it clones the default branch and extracts runnable fenced blocks from the README.
  4. 4Each block runs in a sandboxed shell after the repo's documented install step.
  5. 5A branch checks whether any block failed for that repo.
  6. 6If so, it opens (or updates the existing) GitHub issue titled with the repo name, labeled `docs-drift`, listing the failing snippet and its error output.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect GitHubRepos, issues, pull requests, actions.
  2. 2
    Connect ShellRun sandboxed commands inside the workspace.
  3. 3
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  4. 4
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  5. 5
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.