agentmods.dev

media-upload

media-upload is a skill for Claude Code, Codex from dapi/claude-code-marketplace. It costs 385 tokens per session (6,218 once invoked), scanned B, original, MIT.

A workflow for uploading images and other media files to S3-compatible storage, online file storage that follows the S3 interface, using the MinIO Client. It can also use the latest screenshot taken through Playwright.

In plain words
What is it for?
Uploading screenshots, documents, images, and supported video files; finding the correct source file; and returning a usable public or temporary download URL.
Why use it?
It avoids manually locating files and constructing storage links, while defining whether to return a public CDN link or a temporary signed link.

Skill for Claude CodeCodex

Part of the media-upload plugin — 1 skill shipped together

not rated 16 3d ago B scan 385 tokens original MIT
View the source file dapi/claude-code-marketplace
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.

agentmods
npx agentmods add skills/dapi/claude-code-marketplace/media-upload
Any agent
npx skills add dapi/claude-code-marketplace --skill media-upload
Clone the repo
git clone --depth 1 https://github.com/dapi/claude-code-marketplace

Made for: Claude Code, Codex.

Or install media-upload, the plugin that ships this one along with the rest of its 1 skill.

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 media-upload

README.md
[![agentmods](https://agentmods.dev/badge/skills/dapi/claude-code-marketplace/media-upload.svg)](https://agentmods.dev/skills/dapi/claude-code-marketplace/media-upload)
Your own site
<a href="https://agentmods.dev/skills/dapi/claude-code-marketplace/media-upload"><img src="https://agentmods.dev/badge/skills/dapi/claude-code-marketplace/media-upload.svg" alt="Measured on agentmods" height="20"></a>
Per session 385 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,218 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
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 $0.00385 $0.06218
Opus 5 $0.00192 $0.03109
Sonnet 5 $0.00077 $0.01244
Haiku 4.5 $0.00038 $0.00622

Measured 4d ago against content hash 1e6dfd89cc31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

media-upload scanned grade B with 2 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 4d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 "$HISTORY_FILE"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

HTTP_CODE=$(curl -sI -o /dev/null -w "%{http_code}" "$public_url_full" 2>/dev/null || echo "000")
media-upload/skills/media-upload/SKILL.md · 706 lines

How it starts

The opening of the file, as written. The whole thing — 706 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Media Upload Skill

Загрузка изображений и медиафайлов в S3-совместимое хранилище через mc (MinIO Client) с получением публичной ссылки.

⚠️ CRITICAL: Приоритет URL

ОБЯЗАТЕЛЬНО после загрузки файла:

  1. Если в конфиге есть public_url и url_mode НЕ равен "presigned":

    • СРАЗУ возвращай короткий CDN URL: ${public_url}/${remote_path}
    • НЕ генерируй presigned URL

  2. Только если url_mode: "presigned" или public_url отсутствует:

    • Генерируй presigned URL через mc share download

Пример правильного поведения:

Конфиг: { "public_url": "https://cdn.example.com", "url_mode": "public" }
Путь: 2026/02/03/screenshot.png
→ Возвращай: https://cdn.example.com/2026/02/03/screenshot.png
→ НЕ возвращай: https://s3...?X-Amz-Algorithm=...

Поддерживаемые форматы

Тип Расширения MIME-type
Изображения png, jpg, jpeg, gif, webp, svg image/*
Документы pdf application/pdf
Видео mp4, webm (будущее) video/*

Приоритет определения источника файла

  1. Явный путь — пользователь указал /path/to/file.png в запросе
  2. Playwright MCP — последний результат browser_take_screenshot в текущей сессии
  3. Glob паттерн — "загрузи все png из ./screenshots/"
  4. Спросить пользователя — если ничего не найдено

Интеграция с Playwright MCP

ВАЖНО: Этот скилл должен активироваться АВТОМАТИЧЕСКИ после создания скриншота через Playwright MCP.

Паттерны запросов пользователя

Когда пользователь просит:

  • "открой сайт X и сделай скриншот"
  • "сделай скриншот страницы Y"
  • "take a screenshot of Z"

Алгоритм:

  1. Загрузить инструменты Playwright MCP через ToolSearch
  2. Открыть браузер и перейти на страницу (browser_navigate)
  3. Сделать скриншот (browser_take_screenshot)
  4. АВТОМАТИЧЕСКИ загрузить скриншот в S3 (этот скилл)
  5. Вернуть пользователю публичную ссылку
Формат ответа Playwright

Playwright MCP при вызове browser_take_screenshot возвращает:

Took the viewport screenshot and saved it as /tmp/page-2024-01-31-143052.png

Read the full file on GitHub · 706 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. 4d ago First seen · 706 lines · 385 tokens per session scan B 1e6dfd89cc31

Subscribe to this mod's changes

media-upload is a skill published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 3d ago), licensed MIT. It adds 385 tokens to every session and 6,218 once invoked, about $0.0019 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation
Related

Other skills, from other repositories

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

web-browser

Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.

mitsuhiko/agent-stuff · 64 tokens

traceway-setup

Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…

tracewayapp/traceway · 134 tokens