ENGINEERING
Nightly README code example drift detector
On a nightly schedule, extracts every fenced code block from your README files, runs each one against the latest installed SDK.
How it runs
The automated pipeline, trigger to output.
- TriggerNightly schedule fires
- ActionClone repo and install latest published packageShell
- ActionExtract fenced code blocks from markdown into scriptsShell
- ActionExecute each snippet in a sandbox, capture exit code and stderrShell
- LogicSplit passing vs failing; format failures with file and line
- OutputPost drift digest to SlackSlack
What it does
Documented examples rot silently. This workflow runs every night, pulls every fenced code block out of your README and docs markdown, executes each one in an isolated shell against the currently published version of your library, and reports which examples have broken. You get a single Slack digest listing the exact file, line, and error for every drifted snippet.
When to use it
Use it when your README contains copy-pasteable code samples that must keep working as the API evolves. Ideal for SDKs, CLIs, and libraries where a stale example damages developer trust on first contact.
How it works
- 1A nightly schedule fires the run.
- 2A shell step clones the repo and installs the latest published package version.
- 3A shell step parses all markdown files, extracting fenced blocks tagged as runnable code into individual scripts.
- 4Each extracted snippet is executed in a sandboxed shell; exit codes and stderr are captured.
- 5A logic step splits passing from failing snippets and formats the failures with file path, line number, and error text.
- 6A Slack message delivers the digest, or a quiet all-clear when nothing drifted.
Set it up
What you configure once, before turning it on.
- 1Connect ShellRun sandboxed commands inside the workspace.
- 2Connect SlackChannels, DMs, threads, mentions.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
Upgrade Impact Router to Module Code Owners
Maps a dependency-bump PR's affected modules to their CODEOWNERS, then DMs each owner on Slack with only the changelog slice that touches code they own.
Re-Voice IVR Prompts on Phone-Tree Config Merge
When a phone-tree config change merges in GitHub, regenerates the ElevenLabs audio for any prompt whose script changed in the diff and opens a follow-up PR adding the new audio…
Agent reviews model-license fit and suggests compliant swaps on the PR
When a PR adds a Hugging Face model, an agent reads the model card and license, judges fit against your commercial-use policy.
Scan for deprecated endpoints and email consumers a weekly sunset countdown
On a weekly schedule, scans the OpenAPI spec for endpoints marked deprecated with a sunset date, and emails each consuming team a countdown of how many days remain before removal.
Publish a versioned API changelog to Confluence on each release tag
On a new semver release tag, gathers the contract changes since the last release and writes a clean.
Gate breaking API PRs behind downstream consumer acknowledgement
When a PR introduces a breaking contract change, comments the impact summary back on the PR, applies a blocking label.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.