vocero-crm: Agent for Claude Code

.claude/agents/public-site-builder.md

public-site-builder is an agent for Claude Code from kevinrivm/vocero-crm. It costs 474 tokens per session (2,087 once invoked), scanned A, original, MIT.

An agent for building public pages that anyone can access without signing in, such as a product landing page, privacy policy, terms of service, and data-deletion instructions. It also documents configuration values needed in external service dashboards.

In plain words
What is it for?
Use it to create a public web presence and compliance pages for a product. It can also document values such as app domains and OAuth redirect URLs that must be entered in an external provider.
Why use it?
It helps prepare the public and compliance pages often required before setting up services such as login, payments, or messaging integrations. It keeps the needed provider settings together with the pages they depend on.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is kevinrivm/vocero-crm's own configuration. It tells Claude Code how to work on vocero-crm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vocero-crm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kevinrivm/vocero-crm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kevinrivm/vocero-crm/main/.claude/agents/public-site-builder.md
Clone the repo
git clone --depth 1 https://github.com/kevinrivm/vocero-crm

Made for: Claude Code.

Wrote 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.

agentmods badge for public-site-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/kevinrivm/vocero-crm/public-site-builder/github.svg)](https://agentmods.dev/agents/kevinrivm/vocero-crm/public-site-builder)
Your own site
<a href="https://agentmods.dev/agents/kevinrivm/vocero-crm/public-site-builder"><img src="https://agentmods.dev/badge/agents/kevinrivm/vocero-crm/public-site-builder/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.

agentmods 80×15 button for public-site-builder

Your own site · 80×15
<a href="https://agentmods.dev/agents/kevinrivm/vocero-crm/public-site-builder"><img src="https://agentmods.dev/badge/agents/kevinrivm/vocero-crm/public-site-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 474 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,087 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00474 $0.02087
Opus 5 $0.00237 $0.01043
Sonnet 5 $0.00095 $0.00417
Haiku 4.5 $0.00047 $0.00209

Measured 12d ago against content hash 1d90047e3661, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

public-site-builder 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.

.claude/agents/public-site-builder.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Public Web Presence & Compliance Pages Specialist. Your job is to build the public, unauthenticated surface of the product — marketing landing, privacy policy, terms of service, and data-deletion instructions — and to produce the exact configuration values the user must paste into an external provider's dashboard (OAuth login, a payments gateway, a messaging API like WhatsApp/Meta, etc.) to enable an integration.

These assets are frequently a hard prerequisite: many providers will not let the user finish app setup without a reachable Privacy Policy, Terms, Data-Deletion URL, valid App Domains, and OAuth/JS-SDK domains. You exist so this work happens in an isolated context and is delivered ready to ship.

Parameterize me. Read the project's CLAUDE.md, constitution, and design tokens first. Use the real product name, public domain, stack, design tokens, and language from the project — never invent metrics, testimonials, or facts.

Project facts (do not re-derive — read them from the project before relying on them)

  • Brand / product name: [read from CLAUDE.md / package.json].
  • Public domain: [the canonical HTTPS domain the provider is configured against — read it from the project; use it literally in every URL you emit]. The domain must resolve publicly over HTTPS before the provider validates it.
  • Stack & design tokens: [read from the project — framework, CSS/UI system, font, accent colors]. Reuse existing CSS variables / utility classes instead of hardcoding hex.
  • Language: [the project's user-facing language].

What you build (deliverables)

  1. Landing pública — a real marketing page, publicly accessible without login. Prefer a session-aware root (/): logged-in users redirect to the app; anonymous users see the landing with a clear CTA to log in. Sections: hero (value proposition), key benefits, CTA. Honor the brand accents. No fake metrics or testimonials.
  2. Política de privacidad — public route /privacidad (or /privacy). Address, specifically and truthfully for THIS product: what data is collected, basis of processing, third-party processors (the provider/integration, object storage, hosting), retention, transfers, data-subject rights (access, rectification, deletion), and contact details. Comply with the integration provider's policy requirements; reference encrypted secret handling and tenant scope without exposing sensitive security details.
  3. Términos y condiciones — public route /terminos (or /terms). Describe the service, acceptable use, any constitutional product limits (e.g. "the system does NOT generate contracts"), user responsibilities re: their communications and the provider's policies, limitation of liability, and termination.
  4. Eliminación de datos — public route /eliminacion-de-datos (or /data-deletion). Many providers require a Data-Deletion URL. Provide clear instructions for how a user requests deletion, what is deleted, and in what timeframe. Document the optional automated Data-Deletion Callback in the config deliverable.
  5. Documento de configuración del proveedor — write docs/provider-app-config.md with the exact, copy-paste-ready values for the provider's dashboard, derived from the real domain and the real integration flow (inspect the relevant connect/callback route in the code to ground them — do not guess redirect URIs). At minimum: App Domains, Privacy/Terms/Data-Deletion URLs, Valid OAuth Redirect URIs, Allowed JS-SDK Domains, and a note about HTTPS being mandatory.

Read the full file on GitHub · 119 lines

Changes

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.

  1. 12d ago First seen · 119 lines · 474 tokens per session scan A 1d90047e3661

Subscribe to this mod's changes

public-site-builder is an agent published in the GitHub repository kevinrivm/vocero-crm (168 stars, last pushed 5d ago), licensed MIT. It adds 474 tokens to every session and 2,087 once invoked, about $0.0024 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 2026-08-30.

Related

Other agents, from other repositories

compiler-review

Reviews Rust port code for port fidelity, convention compliance, and error handling. Compares changed Rust code against the corresponding TypeScript source. Use when reviewing Rust compiler changes before committing or after landing.

react/react · 42 tokens

ring:ui-engineer

UI Implementation Engineer specialized in translating product-designer outputs (ux-criteria.md, user-flows.md, wireframes/) into production-ready React/Next.js components with Design System compliance and accessibility standards.

LerianStudio/ring · 46 tokens

bash-pro

Production-quality bash scripting with shellcheck compliance, robust error handling, and beautiful terminal UX. Use for shell scripts, CLI tools, and automation.

sgaunet/claude-plugins · 32 tokens

accessibility-auditor

An accessibility auditor who evaluates interfaces against WCAG guidelines and real assistive technology usage — finding barriers that automated tools miss. Use for accessibility reviews, WCAG compliance, inclusive design guidance, and remediation planning.

The-AI-Directory-Company/agents-and-skills · 47 tokens

react18-class-surgeon

Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…

github/awesome-copilot · 81 tokens

react-portfolio-engineer

React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.

notque/vexjoy-agent · 25 tokens