ask-media

ask-media is a skill for Claude Code, Codex from tallesborges/zdx. It costs 118 tokens per session (1,014 once invoked), scanned A, original, MIT.

A one-shot file-understanding command that sends a local image, PDF, audio, or video to a model and returns an answer about it. You provide a specific question, such as asking for a summary or a detail from a report.

In plain words
What is it for?
Use it to describe images, summarize PDFs, extract information, answer questions about videos, or transcribe audio files.
Why use it?
It lets an agent inspect media files when it cannot read their contents directly, without requiring a separate manual extraction step.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to describe images, summarize PDFs, extract information, answer questions about videos, or transcribe audio files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tallesborges/zdx/ask-media
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 tallesborges/zdx --skill ask-media
Clone the repo
git clone --depth 1 https://github.com/tallesborges/zdx

Made for: Claude Code, Codex.

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 ask-media

README.md
[![agentmods](https://agentmods.dev/badge/skills/tallesborges/zdx/ask-media/github.svg)](https://agentmods.dev/skills/tallesborges/zdx/ask-media)
Your own site
<a href="https://agentmods.dev/skills/tallesborges/zdx/ask-media"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/ask-media/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 ask-media

Your own site · 80×15
<a href="https://agentmods.dev/skills/tallesborges/zdx/ask-media"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/ask-media.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,014 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Excessive Agency · line 49
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 $0.00118 $0.01014
Opus 5 $0.00059 $0.00507
Sonnet 5 $0.00024 $0.00203
Haiku 4.5 $0.00012 $0.00101

Measured 9d ago against content hash fa609d6635c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ask-media 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 9d 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.

crates/zdx-assets/bundled_skills/ask-media/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ask-Media – File understanding via zdx ask-media

Send a local image, PDF, audio, or video file plus a question to a Gemini model and get a text answer back on stdout. One-shot: the file is re-sent on each call.

You write the question, so ask for exactly what you need — not a generic description. A targeted prompt ("read the stack trace and the failing file path") beats "describe this image" every time.

CLI reference

zdx ask-media <FILE> -p "<question>" [OPTIONS]

Options:
  -p, --prompt <PROMPT>   The question/instruction to run against the file (required)
  -m, --model <MODEL>     Gemini provider:model id (default: gemini:gemini-3.5-flash-lite)
      --json              Emit {file, model, answer} JSON instead of plain text

Output: prints the model's text answer to stdout (nothing else). Read it and use it directly in your reply — do not wrap it in a <media> tag (that tag is only for sending files back).

zdx ask-media "$ZDX_ARTIFACT_DIR/report.pdf" -p "Summarize the key findings in 3 bullets."

When to use

  • The user gives you a specific local file path and asks about its contents.
  • The active model cannot read that media type itself. Models without image input (for example deepseek:deepseek-v4-flash) never receive attached images: the image is replaced by a note telling you to come here. The file path is in the surrounding text or tool output — call ask-media on it with a question shaped by what the user actually asked.
  • Supported inputs: images (png/jpg/webp/gif/heic), PDF, audio (mp3/wav/ogg/m4a/aac/flac), and video (mp4/mov/mpeg/webm/flv/wmv/3gp).

When NOT to use

  • The media is already visible to the active model — a vision-capable model receives attached images directly, so just answer. Only reach for ask-media when the content did not reach you.
  • Plain verbatim transcription of an audio file → prefer the transcription skill (zdx transcribe), which is purpose-built for speech-to-text and supports diarization. Use ask-media when the user wants understanding/Q&A/summary over audio or video.
  • Non-Gemini models: ask-media is Gemini-only and errors clearly on any other provider. If no Gemini key is configured, say the file can't be inspected instead of guessing at its contents.

Read the full file on GitHub · 60 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. 9d ago First seen · 60 lines · 118 tokens per session scan A fa609d6635c3

Subscribe to this mod's changes

ask-media is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed 4d ago), licensed MIT. It adds 118 tokens to every session and 1,014 once invoked, about $0.0006 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 skills, from other repositories

wowerpoint

Turn one document into a kawaii NotebookLM slide-deck PDF. Use for "wowerpoint this", "make a deck about ", "turn this report into slides", or any request to render a single document as shareable narrative slides.

thedotmack/claude-mem · 55 tokens

pptx-posters

Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual…

foryourhealth111-pixel/Vibe-Skills · 66 tokens

slides

Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding…

fcakyon/claude-codex-settings · 83 tokens

pptx

Create and validate Microsoft PowerPoint presentations (.pptx), including structured slide decks, tables, workflows, metadata, and reproducible generation scripts. Use for presentation, slides, PowerPoint, PPT, or PPTX creation and verification tasks.

agents-flex/agents-flex · 50 tokens

utility-slideshow-creator

Generates professional presentations from a JSON deck specification using 18 slide types with dark/light variants, content-to-layout decision logic, and calibrated character limits. Ships with a default professional theme.

product-on-purpose/pm-skills · 43 tokens

timecode-audio-edit-workflow

The patch comprehensively addresses all identified issues.

HKUDS/OpenSpace · 0 tokens