Borrowing it
Nothing to install: this file belongs to vuluu2k/webcake-landing-mcp. 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/vuluu2k/webcake-landing-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/vuluu2k/webcake-landing-mcpWrote 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/vuluu2k/webcake-landing-mcp/agents-md)<a href="https://agentmods.dev/instructions/vuluu2k/webcake-landing-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/vuluu2k/webcake-landing-mcp/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/vuluu2k/webcake-landing-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/vuluu2k/webcake-landing-mcp/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 | $0.01161 | $0.01161 |
| Opus 5 | $0.00580 | $0.00580 |
| Sonnet 5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
webcake-landing-mcp 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 8d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — webcake-landing-mcp
Rules for AI agents using this MCP and working on this repo.
Runtime rules (when an LLM uses the webcake-landing tools)
These are also served to the client via the server instructions (see
src/domains/landing/instructions.ts) and the get_generation_guide tool. In short:
- Intake first. Before generating a new page, ask the user 3–6 concrete questions (goal/page type, brand + tone + language, sections in order, primary CTA + destination, form fields, colors/logo URLs, desktop+mobile or mobile-only, which organization) and confirm a short outline. Don't assume.
- No invented facts. Never make up prices, phone numbers, addresses, or statistics — ask or leave a placeholder.
- Validate before persisting. Always
validate_pageand fix every error beforecreate_page/update_page. - Dry-run first.
create_pageandupdate_pagedefault todry_run=true. Show the dry-run; only senddry_run=falseafter the user confirms. - Edit surgically. For an existing page:
get_page→ change ONLY what was asked → keep every other element, itsid, and coordinates →validate_page→update_page. Never regenerate the whole tree for a small change. - Organizations. Call
list_organizations, ask which to use, default to theis_defaultorg. Endpoints are owner-scoped (only the account's own pages). - Model invariants. Popups are a top-level
popuparray (not insidepage); content lives inspecials(notstyles); colors arergba();top/left/width/height/fontSizeare numbers (px); form inputs need a uniquespecials.field_name.
See .claude/skills/webcake-landing/SKILL.md for the full workflow and
docs/page-element-schema.md for the element model.
Repo / dev rules (when editing this codebase)
- TypeScript, ESM, Node 18+. Source in
src/, build todist/vianpm run build(tsc+scripts/copy-assets.mjs, which mirrors everysrc/**/*.jsonintodist/). - After any change:
npm run buildthennpm run smoke(must printALL GOOD) before committing. - Each element is ONE descriptor in
src/domains/landing/elements/<category>.ts(docs +container/fieldflags +defaultName+ factoryseed+example);CONTAINER_TYPES/FIELD_TYPES/the catalog/createElementderive from it. When the model changes, update the descriptor AND theelementTypeenum insrc/domains/landing/page-schema.json(+validate.tsonly for a new semantic rule), then rebuild + smoke. - New tools go in a
src/tools/*.tsgroup; backend HTTP calls insrc/persistence/webcake-client.ts; element knowledge + default node shapes insrc/domains/landing/elements/; validation insrc/domains/landing/validate.ts; domain-agnostic primitives insrc/core/. - Two transports share
createServer()(src/server.ts): stdio (default) and a remote Streamable-HTTP server (node dist/index.js serve [--port N] [--env local|staging|prod],src/http.ts). In HTTP mode credentials are per-request via headers (x-webcake-jwt/Authorization: Bearer,x-webcake-env,x-webcake-org-id, …; seesrc/persistence/config.ts#configFromHeaders), falling back to env — so a hosted server is multi-user. node dist/index.js login(src/auth/login.ts) grabs the JWT via the browser (a localhost loopback receives a redirect from the Webcake/mcp-connectendpoint that reads thejwtcookie) and saves it to~/.webcake-landing-mcp/auth.json.readConfigprecedence: per-request overrides → env → that file.WEBCAKE_ENV/--env(local|staging|prod, theENVIRONMENTStable inconfig.ts) supplies the default API + app base URLs; explicitWEBCAKE_API_BASE/WEBCAKE_APP_BASEstill win.- Never commit secrets. The JWT is read from the
WEBCAKE_JWTenv var only — never hard-code a token, account, or page data in the repo. Scan before pushing (the repo is public). - The backend endpoints this MCP calls live in
landing_page_backend(LandingPageWeb.V1.AiController, scope/api/v1/ai).
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.
- 8d ago First seen · 62 lines · 1,161 tokens per session scan A 93fbb455d215
webcake-landing-mcp AGENTS.md is an instructions file published in the GitHub repository vuluu2k/webcake-landing-mcp (5 stars, last pushed 14d ago), licensed MIT. It adds 1,161 tokens to every session, about $0.0058 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.