Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Optimize Framer costs through tier selection, sampling, and usage monitoring. Use when analyzing Framer billing, reducing API costs, or implementing usage monitoring and budget alerts. Trigger with phrases like "framer cost", "framer billing", "reduce framer costs", "framer pricing", "framer expensive", "framer budget".
.claude/skills/jeremylongshore-framer-cost-tuning/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -12% | 0% |
Optimize Framer costs across plans and features. The Server API is free during beta. Main costs are Framer site plans, custom domains, and team seats.
| Plan | Price | CMS Items | Custom Domain | Pages | |------|-------|-----------|---------------|-------| | Free | $0 | 100 | No | 2 | | Mini | $5/mo | 200 | Yes | 150 | | Basic | $15/mo | 1,000 | Yes | 300 | | Pro | $30/mo | 10,000 | Yes | Unlimited | | Enterprise | Custom | Unlimited | Yes | Unlimited |
typescript// Track CMS item usage to avoid plan overages async function checkCMSUsage(client: any) { const collections = await client.getCollections(); let totalItems = 0; for (const col of collections) { const items = await col.getItems(); totalItems += items.length; console.log(`${col.name}: ${items.length} items`); } console.log(`Total CMS items: ${totalItems}`); // Pro plan: 10,000 limit console.log(`Usage: ${((totalItems / 10000) * 100).toFixed(1)}% of Pro limit`); }
typescript// Batch CMS updates before publishing (each publish rebuilds the site) async function batchUpdateAndPublish(updates: Array<{ collection: string; items: any[] }>) { const client = await getClient(); for (const update of updates) { const col = (await client.getCollections()).find(c => c.name === update.collection); if (col) await col.setItems(update.items); } // Single publish after all updates await client.publish(); }
Use a free plan site for development and testing. Only pay for the production site.
For architecture patterns, see framer-reference-architecture.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,349 | 17,479 | -18% | 1 | 1 | 0% | 2,868 | 2,925 | +2% | 0 | 0 | — |
case-02 | fail→pass | 16,634 | 16,565 | -0% | 1 | 1 | 0% | 2,364 | 2,751 | +16% | 0 | 0 | — |
case-03 | fail→pass | 11,339 | 8,756 | -23% | 1 | 1 | 0% | 1,210 | 1,253 | +4% | 0 | 0 | — |
case-04 | pass→pass | 10,775 | 2,802 | -74% | 1 | 1 | 0% | 1,045 | 1,042 | -0% | 0 | 0 | — |
case-05 | fail→pass | 8,751 | 11,509 | +32% | 1 | 1 | 0% | 1,541 | 1,706 | +11% | 0 | 0 | — |
case-06 | pass→pass | 20,401 | 19,423 | -5% | 1 | 1 | 0% | 2,525 | 3,206 | +27% | 0 | 0 | — |
case-07 | pass→pass | 10,624 | 9,806 | -8% | 1 | 1 | 0% | 1,668 | 1,365 | -18% | 0 | 0 | — |
case-08 | pass→pass | 19,465 | 8,221 | -58% | 1 | 1 | 0% | 2,297 | 1,900 | -17% | 0 | 0 | — |
case-09 | pass→pass | 14,307 | 10,832 | -24% | 1 | 1 | 0% | 1,998 | 1,744 | -13% | 0 | 0 | — |
case-10 | fail→pass | 12,885 | 9,061 | -30% | 1 | 1 | 0% | 1,534 | 1,344 | -12% | 0 | 0 | — |
case-11 | pass→pass | 12,447 | 7,022 | -44% | 1 | 1 | 0% | 1,314 | 1,745 | +33% | 0 | 0 | — |
case-12 | fail→pass | 19,952 | 13,174 | -34% | 1 | 1 | 0% | 3,959 | 2,173 | -45% | 0 | 0 | — |
case-13 | pass→pass | 7,299 | 9,467 | +30% | 1 | 1 | 0% | 1,416 | 1,321 | -7% | 0 | 0 | — |
case-14 | pass→pass | 9,812 | 3,430 | -65% | 1 | 1 | 0% | 1,980 | 1,204 | -39% | 0 | 0 | — |
case-15 | fail→pass | 12,290 | 12,295 | +0% | 1 | 1 | 0% | 2,095 | 1,815 | -13% | 0 | 0 | — |
case-16 | pass→pass | 4,869 | 1,988 | -59% | 1 | 1 | 0% | 824 | 913 | +11% | 0 | 0 | — |
case-17 | pass→pass | 14,686 | 4,709 | -68% | 1 | 1 | 0% | 1,655 | 1,478 | -11% | 0 | 0 | — |
case-18 | pass→fail | 20,951 | 11,561 | -45% | 1 | 1 | 0% | 2,523 | 2,674 | +6% | 0 | 0 | — |
case-19 | pass→pass | 10,645 | 4,822 | -55% | 1 | 1 | 0% | 1,882 | 1,491 | -21% | 0 | 0 | — |
case-20 | fail→pass | 14,565 | 7,193 | -51% | 1 | 1 | 0% | 1,976 | 2,024 | +2% | 0 | 0 | — |
case-21 | pass→pass | 11,601 | 9,411 | -19% | 1 | 1 | 0% | 2,677 | 2,697 | +1% | 0 | 0 | — |
case-22 | pass→pass | 14,151 | 8,637 | -39% | 1 | 1 | 0% | 1,830 | 2,328 | +27% | 0 | 0 | — |
case-23 | pass→pass | 5,621 | 10,210 | +82% | 1 | 1 | 0% | 1,300 | 1,658 | +28% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +30 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.