Borrowing it
Nothing to install: this file belongs to oekazuma/svelte-vitals. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/oekazuma/svelte-vitals/main/AGENTS.mdgit clone --depth 1 https://github.com/oekazuma/svelte-vitalsWrote 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/instructions/oekazuma/svelte-vitals/agents-md)<a href="https://agentmods.dev/instructions/oekazuma/svelte-vitals/agents-md"><img src="https://agentmods.dev/badge/instructions/oekazuma/svelte-vitals/agents-md/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/instructions/oekazuma/svelte-vitals/agents-md"><img src="https://agentmods.dev/badge/instructions/oekazuma/svelte-vitals/agents-md.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 | $0.04824 | $0.04824 |
| Opus 5.5 | $0.01930 | $0.01930 |
| Sonnet 5.5 | $0.00965 | $0.00965 |
| Haiku 4.5 | $0.00482 | $0.00482 |
Grade A, and why
svelte-vitals AGENTS.md 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 12d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository conventions for AI agent sessions. Read this before exploring the codebase — it exists so you don't have to rediscover (or guess) these facts every session.
What this is
svelte-vitals is a static code-health checker for SvelteKit — not a runtime Web Vitals reporter. It statically analyzes source code (resolved <head> metadata and component bodies) across six categories: SEO, Performance, Correctness, Security, Architecture, Accessibility. The project is pre-1.0 (all packages are on 0.x versions).
Verify commands
| Purpose | Command | Notes |
|---|---|---|
| Build | pnpm build |
pnpm -r build |
| Typecheck | pnpm typecheck |
pnpm -r typecheck |
| Test | pnpm test |
pnpm build && pnpm -r test (vitest) — builds first because packages/cli's tests import @svelte-vitals/core from its built dist |
| Floor smoke | pnpm smoke |
needs pnpm build first — it runs the built dist under a bare node; locally that is the devEngines Node, not the floor, so the floor claim is what CI's floor-smoke job (pinned to 24.16.0) adds |
| Ecosystem | pnpm ecosystem |
needs pnpm build first — clones the third-party SvelteKit apps listed in scripts/ecosystem-smoke.js and asserts only "no crash, exit ∈ {0,1}, report parses"; scheduled weekly, never PR-blocking |
| Corpus | pnpm corpus update |
manual, needs pnpm build first — measures every rule on the pinned apps in scripts/corpus/targets.json, joins the verdicts in scripts/corpus/verdicts/ (one file per app), and rewrites measurement.json plus the table in scripts/corpus/README.md (then pnpm format). run/diff are what the corpus.yml PR job uses. See docs/superpowers/specs/2026-09-23-corpus-precision-design.md |
| Lint | pnpm lint |
oxlint . + oxfmt --check . + pnpm lint:docs (textlint @textlint-ja/preset-ai-writing plus a curated preset-ja-technical-writing over READMEs, packages/cli/docs/, and the docs site's .md pages — .mdx pages are not linted. Config in .textlintrc.json; its disabled rules were each measured noisy on this corpus, so don't re-enable one without re-measuring) |
| Format | pnpm format |
oxfmt --write . |
| Publish checks | pnpm check:publish |
publint + attw (--profile esm-only) |
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.
- 12d ago Changed b4af7d58fdc1
- 20d ago Changed · +12 tokens per session aa04a391b052
- 27d ago Changed · +31 tokens per session a465a1c8b328
- 28d ago Changed · +2 lines · +115 tokens per session c99baac60af0
- 1mo ago Changed · +1 lines · +290 tokens per session a782adfa7000
- 1mo ago Changed · +2 lines · +53 tokens per session 9d8563e32c40
- 1mo ago Changed · -13 tokens per session ef51b42d8e58
- 1mo ago First seen · 157 lines · 4,336 tokens per session scan A bc2987d4ed48
svelte-vitals AGENTS.md is an instructions file published in the GitHub repository oekazuma/svelte-vitals (24 stars, last pushed today), licensed MIT. It adds 4,824 tokens to every session, about $0.0193 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.