ENGINEERING
Agentic Flag-Cleanup Sweep With Test Validation
An agent audits the codebase for stale feature flags, removes each one branch-by-branch, runs the test suite in a shell sandbox to prove nothing broke.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled sweep launches agent
- ActionList stale fully-rolled-out flags from PostgresPostgres
- ActionLocate refs and remove flag keeping live pathGitHub
- ActionRun test suite in shell sandboxShell
- LogicRoute green to PR, red to report
- ActionOpen verified PR for passing flagsGitHub
- OutputPost test-failing flags to SlackSlack
What it does
Goes beyond pattern-matching: an agent reasons through each stale flag's removal, edits the affected files, executes the project's tests, and only ships a PR when the suite is green. Failing removals are reported instead of forced.
When to use it
Use it when flag usage is inconsistent enough that mechanical rewrites are risky and you want test-backed confidence before any cleanup PR opens. Best for repos with a fast, reliable test command.
How it works
- 1A scheduled sweep launches the cleanup agent.
- 2The agent queries Postgres to list flags that are fully rolled out and past the grace window.
- 3For each flag, it locates references in GitHub and removes the flag, keeping the live path.
- 4It runs the test suite in a shell sandbox against the edited tree.
- 5A logic step routes green removals to a PR and red ones to a report.
- 6It opens a verified GitHub PR for passing flags and posts the skipped, test-failing flags to Slack for manual review.
Set it up
What you configure once, before turning it on.
- 1Connect PostgresAny Postgres URL — query, write, migrate.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect ShellRun sandboxed commands inside the workspace.
- 4Connect SlackChannels, DMs, threads, mentions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
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.
Block PRs that add incompatible Hugging Face model licenses
When a pull request adds or bumps a Hugging Face model dependency, it fetches the model card license, checks it against your org's allowed-license policy.
Quarterly Logging Hygiene Audit Agent
An agent-driven quarterly sweep that surveys all Axiom datasets, builds a logging-hygiene scorecard per service.
Post-Merge Log Volume Recheck After Downsampling PR
After a log-level PR merges, waits a day then re-queries Axiom to confirm the targeted stream's volume actually dropped.
Axiom Ingest Cost Spike to Linear Triage Ticket
When Axiom ingest volume spikes beyond its baseline, identifies which service caused it and files a Linear ticket with the offending log stream, sample lines, and a downsampling…
File a Linear license-review ticket for risky model adds
When a PR introduces a Hugging Face model with a non-permissive or unknown license, it opens a Linear issue assigned to the legal-review team with the model, license.
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.