/goalperformancemedium riskintermediatesafety D · 50 · open-endedForward Futurepre-dates current gate · under review

Get every page under 50 ms

Benchmark each page with one repeatable measure and keep optimizing until every target loads under the threshold.

prompt
→ Claude
Continue optimizing the code for speed. After each significant change, measure page-load performance across every page under the same repeatable test conditions. Continue until every page loads in under 50 ms.
claude-code · codex

Use this when

Use this when a product has a defined set of routes, a stable performance harness, and a 50 ms target that maps to a specific metric and environment.

How it runs

  1. Define the exact metric, routes, test environment, warm-up behavior, and number of benchmark runs.
  2. Capture a baseline for every target page before making changes.
  3. Make one significant optimization, rerun the same benchmark, and inspect regressions across all routes.
  4. Continue until every page meets the threshold under the original test conditions.

Done when

Every page loads in under 50 ms. Use the same benchmark and confirm there are no regressions.

Why it works

The fixed harness prevents performance work from turning into anecdotal tuning. Measuring every route after each change catches local wins that quietly slow down another page.

Implementation note

Page load can mean server response, render completion, or a browser timing metric. Name the metric and hardware explicitly so the 50 ms target is reproducible and meaningful.

Source: Forward Future

More performance loops

Benchmark regression watch

/looploopreponew

Run the benchmark suite every 30 minutes during active development and raise a flag the moment any benchmark slips more than 5 percent from baseline.

prompt
→ Claude
/loop 30m run `npm run bench`, compare each result to the baselines in bench/baseline.json, and if any benchmark regressed more than 5%, show me the numbers and the commits since the last clean run
performancemedium risk

Bundle size budget

/goalloopreponew

Shrink the production JavaScript bundle under a hard budget by attacking the largest modules with code-splitting, lighter imports, and dead-weight removal.

prompt
→ Claude
/goal the main production bundle is under 250 KB gzipped — run the build with the bundle analyzer, address the single largest contributor each turn (code-split it, replace it with a lighter import, or drop it), and confirm the build and tests stay green; stop at the budget or after 10 turns
performancemedium risk

AutoLoop — metric-driven optimization loops

/ralphnew

Agent-agnostic hill-climbing loops inspired by Karpathy's autoresearch: define a metric, let the agent propose a change, measure, keep it only if the number improved, and repeat.

prompt
→ Claude
Iterative optimization loops (inspired by Karpathy's autoresearch): define a metric, agent proposes change, harness measures, keep if improved, repeat. Works with Claude Code, Codex, Cursor, Gemini CLI.
performancemedium risk