/loopdevopshigh riskintermediatesafety D · 40 · open-endedForward Futurepre-dates current gate · under review

Capture a post-release baseline

Run the standard benchmarks against a finished release and record a reproducible baseline for future comparison.

prompt
→ Claude
After current releases finish, run the standard benchmarks and record the results as the new baseline.
claude-code · codex

Use this when

Use this immediately after a release when future regressions or improvements need to be measured against the exact version now in production.

How it runs

  1. Confirm every in-scope release is complete and record the production revision or artifact identity.
  2. Run the standard benchmark suite under its documented environment, data, warm-up, and repetition rules.
  3. Investigate invalid or unstable runs, then rerun only under the same documented conditions.
  4. Store the final results with the release identity and benchmark metadata, and mark them as the new comparison baseline.

Done when

The new baseline belongs to the completed release. Revision, environment, benchmark version, conditions, and results are recorded together.

Why it works

Tying the baseline to a verified release creates a trustworthy reference point for later performance and quality work. Recording the conditions prevents unrelated environment changes from masquerading as product changes.

Implementation note

Do not overwrite the previous baseline until the release identity and benchmark run are verified. Keep historical baselines available for trend analysis.

Source: Forward Future

More devops loops

Check whether the deploy finished and summarize what changed

/loopnew

A 5-minute watch loop that polls whether a deploy has finished and, once it lands, summarizes what changed. It is a read-only status watcher rather than an agent driving toward a finish condition.

prompt
→ Claude
/loop 5m check whether the deploy finished and summarize what changed
devopshigh risk

Deploy-poll loop

A hands-free ops loop that polls your deploy every two minutes, runs the smoke test the moment it goes live, and stops with a report if any check fails.

prompt
→ Claude
/loop every 2 minutes: check deploy status; when it's live, run the smoke test and summarize; if smoke test fails, report the failing check and stop
devopsmedium risk

Docker image slimming

/goalloopreponew

Iteratively shrink a Docker image under a size target using multi-stage builds, smaller base images, and layer cleanup, verifying the container still boots each turn.

prompt
→ Claude
/goal `docker images` shows the app image under 300 MB — apply one slimming change per turn (multi-stage build, slimmer base image, prune build deps, consolidate layers), rebuild, and verify the container starts and passes its healthcheck before the next change; stop at the target or after 8 turns
devopslow risk