agentmods.dev

bynn

A document and identity verification add-on that checks PDF and image files for fraud, including manipulation and AI-generated content. It also supports identity checks, age checks, content moderation, face searches, invitations, and webhook verification.

In plain words
What is it for?
Use it for document-fraud checks, know-your-customer identity sessions, age verification, content moderation, face search, AutoDoc invitations, and verifying webhook messages.
Why use it?
It helps applications assess whether submitted documents or identity information may be fake or altered, and supports related verification workflows.

Plugin for Claude Code

0 8d ago A scan tokens not measured original MIT
View the source file Bynn-Intelligence/skills
Install

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.

Claude Code
/plugin marketplace add Bynn-Intelligence/skills
agentmods
npx agentmods add plugins/bynn-intelligence/skills/bynn
Clone the repo
git clone --depth 1 https://github.com/Bynn-Intelligence/skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

bynn 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 yesterday.

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.

plugins/bynn/.claude-plugin/plugin.json · 40 lines

What it actually says

{
  "name": "bynn",
  "version": "1.0.0",
  "description": "Document fraud detection for manipulated, fake and AI-generated PDF and image documents, plus identity verification and KYC sessions, age verification, content moderation, face search, AutoDoc invitations, and webhook verification. Bundles the Bynn MCP server.",
  "license": "MIT",
  "author": {
    "name": "Bynn Intelligence",
    "url": "https://www.bynn.com"
  },
  "homepage": "https://docs.bynn.com",
  "repository": "https://github.com/Bynn-Intelligence/skills",
  "keywords": [
    "bynn",
    "kyc",
    "identity-verification",
    "document-fraud",
    "aml",
    "deepfake",
    "mcp"
  ],
  "mcpServers": {
    "bynn": {
      "type": "http",
      "url": "https://mcp.bynn.com"
    }
  },
  "skills": [
    "./skills/bynn",
    "./skills/bynn-mcp",
    "./skills/bynn-kyc-sessions",
    "./skills/bynn-web-sdk",
    "./skills/bynn-document-fraud",
    "./skills/bynn-age-verification",
    "./skills/bynn-moderation",
    "./skills/bynn-face-search",
    "./skills/bynn-autodoc",
    "./skills/bynn-webhooks"
  ]
}
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. yesterday First seen · 40 lines scan A 66a9656c62c4

Subscribe to this mod's changes

bynn is a plugin published in the GitHub repository Bynn-Intelligence/skills (0 stars, last pushed 8d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Content ModerationDocumentsResearchWriting and docsage-verificationagent-skillsai-agentsdocument-fraud-detectionidentity-verification
Related

Other plugins, from other repositories

tone-police

Automatically filters angry, hostile, and profane language from user prompts before they reach Claude. Preserves intent while replacing hostility with constructive phrasing.

zircote-plugins/tone-police · not measured

nextjs

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

vercel/next.js · not measured

nextjs

Official Claude Code plugin marketplace for Next.js, serving the skills that ship in the vercel/next.js repository.

vercel/next.js · not measured

claude-plugins-official

Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.

anthropics/claude-plugins-official · not measured

knowledge-work-plugins

Plugin marketplace listing 97 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.

anthropics/knowledge-work-plugins · not measured

ecc

Plugin marketplace listing 1 plugin: ecc.

affaan-m/ECC · not measured