agentmods.dev

mcp-app-verification

mcp-app-verification is a skill for Claude Code from a5c-ai/babysitter. It costs 48 tokens per session (3,084 once invoked), scanned A, original, MIT.

A verification checklist for MCP Apps, which are interactive apps that connect to an MCP host. It checks runtime behavior, event setup, bundled output, host styling, browser security rules, and removal of outdated patterns.

In plain words
What is it for?
Use it before deploying or migrating an MCP App. It helps run the app in a reference host, verify event handlers and fallbacks, inspect the single-file bundle, check content-security rules, and find legacy code.
Why use it?
It catches compatibility and deployment problems that may not appear from reading the source alone. The checks cover both whether the app works and whether its build and integration follow required conventions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

not rated 1.8krepo +14 4d ago A scan SkillSpector: pass 48 tokens original MIT

Good fit Use it before deploying or migrating an MCP App. It helps run the app in a reference host, verify event handlers and fallbacks, inspect the single-file bundle, check content-security rules, and find legacy code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a5c-ai/babysitter/mcp-app-verification
View source ↗ a5c-ai/babysitter a5c.ai
About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,783 stars · on GitHub · a5c.ai

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.

Any agent
npx skills add a5c-ai/babysitter --skill mcp-app-verification
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

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 mcp-app-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/a5c-ai/babysitter/mcp-app-verification/github.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/mcp-app-verification)
Your own site
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/mcp-app-verification"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/mcp-app-verification/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 mcp-app-verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/mcp-app-verification"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/mcp-app-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,084 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00048 $0.03084
Opus 5 $0.00024 $0.01542
Sonnet 5 $0.00010 $0.00617
Haiku 4.5 $0.00005 $0.00308

Measured 5d ago against content hash 6567b98e4079, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-app-verification 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.

library/specializations/ai-agents-conversational/skills/mcp-app-verification/SKILL.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-app-verification

Run comprehensive verification checklists for MCP Apps covering correctness, compatibility, and migration completeness.

Overview

MCP Apps have several critical invariants that must be verified before deployment. This skill provides systematic verification across multiple dimensions:

  1. Runtime verification: App loads and functions in basic-host reference
  2. Pattern verification: Critical code patterns are correct (handler-before-connect, text fallback)
  3. Build verification: Single-file bundle is valid and complete
  4. Styling verification: Host theming applies correctly
  5. CSP verification: All origins declared, no silent failures
  6. Migration verification: No remaining legacy patterns (OpenAI, old MIME types, snake_case)

Capabilities

basic-host Test Execution

  • Build the MCP App
  • Start the server
  • Launch basic-host reference implementation against the server
  • Verify app loads without console errors
  • Verify handlers fire correctly

Handler-Before-Connect Invariant

  • Search source code for app.connect() call
  • Verify ALL handlers (ontoolinput, ontoolresult, onhostcontextchanged, onteardown) are registered BEFORE connect
  • Flag violations -- handlers registered after connect will silently not work

Text Fallback Verification

  • Search all tool handlers for content array in return value
  • Verify each tool returns at least one { type: 'text', text: '...' } entry
  • Flag tools that only return structuredContent without text fallback

Resource URI Link Integrity

  • Extract all resourceUri values from registerAppTool calls
  • Extract all URIs from registerAppResource calls
  • Verify every tool resourceUri has a matching registered resource
  • Flag orphaned resources (registered but not referenced)

Single-File Bundle Verification

  • Build the project
  • Verify dist/mcp-app.html (or equivalent) exists
  • Check the HTML file is self-contained (no external <script src>, <link href>, <img src> to relative paths)
  • Verify vite-plugin-singlefile is in dev dependencies

Read the full file on GitHub · 348 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 348 lines · 48 tokens per session scan A 6567b98e4079

Subscribe to this mod's changes

mcp-app-verification is a skill published in the GitHub repository a5c-ai/babysitter (1,783 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 3,084 once invoked, about $0.0002 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 2026-09-05.

Building agentsTestingagent-orchestrationagent-skillsagentic-aiagentic-workflowai-automationbabysitter
Related

Other skills, from other repositories

goga-accept-test-assessment

Cell test coverage assessment for acceptance review.

qarium/goga · 15 tokens

goga-accept-usage-review

Validate cell-level usage files against actual implementation during acceptance.

qarium/goga · 18 tokens

goga-accept-scope

Defines the acceptance scope — the set of cells for a given functionality.

qarium/goga · 20 tokens

goga-change-test-engineer

Test Coverage Validation and Behavioral Testing.

qarium/goga · 13 tokens

rn-testing

This skill should be used when the user asks to "write a Maestro test", "create E2E flows", "add testIDs", "run UI tests", "run E2E tests", "verify a feature works", "test my screen", "set up maestro-runner", "mock network requests", "inspect store state", "write test assertions", or needs guidance on test timing…

Lykhoyda/rn-dev-agent · 106 tokens

capturing-proof

This skill should be used when the user asks to "capture proof", "record a demo of this feature", "make a video showing it works", "record the flow for the PR", "generate a PR body", "capture screenshots for the PR", "proof-capture", or when a verified feature needs PR-ready proof artifacts (video + numbered…

Lykhoyda/rn-dev-agent · 105 tokens