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 agentmods add instructions/eplecheck/vibecheck/claude-mdgit clone --depth 1 https://github.com/EpleCheck/vibecheckWrote 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/eplecheck/vibecheck/claude-md)<a href="https://agentmods.dev/instructions/eplecheck/vibecheck/claude-md"><img src="https://agentmods.dev/badge/instructions/eplecheck/vibecheck/claude-md.svg" alt="Measured on agentmods" 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 | $0.01570 | $0.01570 |
| Opus 5 | $0.00785 | $0.00785 |
| Sonnet 5 | $0.00314 | $0.00314 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
vibecheck CLAUDE.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 5d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VibeCheck — repo guide
VibeCheck is "the CMS you talk to": a git-backed, schema-safe headless CMS you edit by chatting with an AI agent. A page is typed data, not markup, so machine-generated content can't break the build. This file orients both Claude and human contributors working in the repo.
Requirements
- Node 22+ and npm (uses workspaces)
- git
- Optional, only to run the MCP server: a GitHub token and (for the container) Docker
Layout (npm-workspaces monorepo)
packages/schema @vibecheck/schema — the content contract (zod). Single source of truth.
apps/site the Astro site — renderer + content. Deploys as static HTML.
apps/mcp @vibecheck/mcp — the MCP server (lets an agent edit from anywhere).
site and mcp both import @vibecheck/schema — never define a schema in two
places.
Setup & commands
npm install
npm run build # build:schema -> build:site (validates content) -> typecheck:mcp
npm run dev -w site # local preview at http://localhost:4321
Editing content (the main task)
Pages are YAML in apps/site/src/content/pages/**/*.yaml. A page is a title plus a
list of typed sections:
hero | features | pricing | cta | richtext | faq | testimonials | embed | heading | image | gallery | divider | spacer | iconlist | form.
Only richtext carries raw HTML.
- Add/edit a page → edit the YAML directly.
home.yamlis the front page. - A nested file
a/b.yamlbecomes/a/b/and gets an automatic breadcrumb. - Always run
npm run buildbefore committing — it validates every page against the schema. A green build means the content is valid (this is exactly what CI runs).
Reach for a typed section before richtext
richtext is the escape hatch, not the default — raw HTML is the one thing that can
break the build, so prefer a typed section whenever one fits:
- FAQ → use the
faqsection (faq.yamlis the worked example). It emitsFAQPageJSON-LD for SEO; faking one withfeaturesorrichtextdoes not. - Testimonials/reviews → use the
testimonialssection (home.yamlis the worked example). It emitsReviewJSON-LD; setsubjectso each review names what it's reviewing. Don't fake quotes withfeaturesorrichtext. - Feature/service grid, team →
features(title + body, optional image/href). Don't hand-write card markup inrichtext. - Video (YouTube/Vimeo) → use the
embedsection (about.yamlis the worked example). It builds the iframe from an allowlisted provider + bare id, so a raw<iframe>inrichtextis never needed (and is the kind of HTML that can break the build). - Plans/tiers →
pricing. Lead-in + button →heroorcta. - A single image → use the
imagesection (requiredalt, optional caption/link), not an<img>inrichtext. Several images →gallery(gridorcarousel).components.yamlis the worked example for both. - A section heading on its own →
heading(h2/h3). A checklist / feature ticks →iconlist(allowlisted icon names, never raw SVG). A rule / vertical gap →divider/spacer. All shown incomponents.yaml.
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.
- 5d ago First seen · 130 lines · 1,570 tokens per session scan A fe0fd293797e
vibecheck CLAUDE.md is an instructions file published in the GitHub repository EpleCheck/vibecheck (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,570 tokens to every session, about $0.0078 per session on Opus 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.
Other instructions, from other repositories
payload CLAUDE.md
Claude Code instructions for payloadcms/payload, covering claude.md, project structure, key directories, architecture notes and quick start.
emdash AGENTS.md
AGENTS.md instructions for emdash-cms/emdash, covering rules, workflow, architecture, code patterns and database: never interpolate into sql.
payload AGENTS.md
AGENTS.md instructions for payloadcms/payload, a project described as: Payload is the open-source, fullstack Next.js framework, giving you instant backend superpowers. Get a full TypeScript backend and admin panel instantly. Use Payload as a headless CMS or for building powerful applications.
sonicjs AGENTS.md
AGENTS.md instructions for SonicJs-Org/sonicjs, covering sonicjs agent guidelines, decision tree — code exploration, rtk (rust token killer), caveman mode and delegation — cavecrew subagents.
sonicjs CLAUDE.md
Claude Code instructions for SonicJs-Org/sonicjs, covering sonicjs ai development guidelines, core technology stack, workspace boundary (conductor), architecture direction: document model (authoritative) and the 5 document tables (migration 0002documents.sql).
flowwink CLAUDE.md
Claude Code instructions for magnusfroste/flowwink, covering claude.md, commands, development (auto-runs migrations before starting), production build and lint.