Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fubits1/svelte-skills --skill migrationgit clone --depth 1 https://github.com/fubits1/svelte-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fubits1/svelte-skills/migration)<a href="https://agentmods.dev/skills/fubits1/svelte-skills/migration"><img src="https://agentmods.dev/badge/skills/fubits1/svelte-skills/migration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fubits1/svelte-skills/migration"><img src="https://agentmods.dev/badge/skills/fubits1/svelte-skills/migration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.01682 |
| Opus 5.5 | $0.00020 | $0.00673 |
| Sonnet 5.5 | $0.00010 | $0.00336 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
migration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migration
Framework upgrades, major dep bumps, config migrations. The core challenge is proving zero regressions, which requires baselines captured on the TRUE pre-change state.
Rule Zero: Check Working Tree FIRST
Before planning, researching, or writing anything:
git status
git diff package.json
If package.json is already modified, deps may already be upgraded. Baselines taken now reflect post-upgrade state and are WORTHLESS for comparison. You must restore old deps before capturing baselines (see Phase 3a).
If package.json is clean, capture all baselines before touching it.
This is non-negotiable. Baselines on upgraded deps cannot prove zero regressions. Ask yourself: "What state was the code in BEFORE any migration work started?" That is the state you baseline against.
Phase 1: Research
REQUIRED: Use agent:research skill. All four channels, local investigation, docs/MCPs, online research, verify and synthesize.
For each breaking change found in the migration guide, grep the codebase to check if it applies. Don't assume, verify.
Output: A list of concrete changes needed, with file paths and line numbers.
Phase 2: Ask Before Assuming
Do NOT assume version numbers (.nvmrc, TypeScript, etc.), which config blocks to keep or remove, or whether a deprecated pattern should be cleaned up. ASK.
Phase 3: Baseline Capture
3a: Restore Pre-Upgrade State (if deps already changed)
git stash
pnpm install
# verify project builds with OLD deps
3b: Capture Baselines
- Build output: full log, page count
- Sitemap: copy XML files, extract every
<loc>URL to flat list - Screenshot every route: Playwright MCP, every sitemap URL, assert no console errors
- Measure page sections: per
frontend:pixel-perfect:getBoundingClientRect()on every visible section, save as JSON - Run existing tests: save output, record pass/fail counts
3c: Restore Upgraded State
git stash pop
pnpm install
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 171 lines · 50 tokens per session scan A 2acd9f4bf486
migration is a skill published in the GitHub repository fubits1/svelte-skills (10 stars, last pushed 12d ago), licensed MIT. It adds 50 tokens to every session and 1,682 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
migration compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| migrationfubits1/svelte-skills | Skill | 10 | 12d ago | MIT | A | 50 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |