ENGINEERING
Agent-Driven Codebase Sweep to Plan Flag Removals
An agent crawls the repository for every feature-flag reference, cross-checks each against rollout state, and produces a prioritized removal plan with per-flag risk notes.
How it runs
The automated pipeline, trigger to output.
- TriggerManual kickoff of cleanup initiative
- ActionAgent scans GitLab repo for flag references and contextGitLab
- ActionQuery Postgres for per-flag rollout statePostgres
- LogicAgent reasons about removal risk and effort per flag
- ActionWrite prioritized removal plan to ConfluenceConfluence
- OutputPost Slack summary with top safe removalsSlack
What it does
Uses an agent to perform a holistic sweep: it reads the actual code around each flag usage, understands whether the disabled branch still contains logic worth preserving, correlates that with rollout data, and writes a reasoned removal plan ranking flags by safety and effort rather than age alone.
When to use it
Reach for this before a dedicated debt-burndown sprint, when a simple age query is too blunt. The agent distinguishes a flag wrapping a trivial UI toggle from one gating a risky data-migration path, so the team starts with the genuinely safe wins. Run it quarterly or ahead of a major refactor.
How it works
- 1Triggered manually when the team kicks off a cleanup initiative.
- 2The agent scans GitLab repository contents for all flag-key references and their surrounding code.
- 3It queries Postgres rollout state to label each flag fully-on, partial, or dormant.
- 4The agent reasons per flag about removal risk, dead-branch contents, and effort.
- 5It writes a prioritized removal plan to a Confluence page with risk notes and ordering.
- 6It posts a Slack summary linking the plan and highlighting the top safe removals.
Set it up
What you configure once, before turning it on.
- 1Connect GitLabRepos, MRs, pipelines, registry.
- 2Connect PostgresAny Postgres URL — query, write, migrate.
- 3Connect ConfluenceSpaces, pages, blueprints.
- 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.