What is media-authenticity?

A media-checking skill that sends a selected audio file, image, or video to Resemble AI to estimate whether it contains synthetic manipulation.

Use it to investigate suspected deepfakes, AI-generated images, synthetic video, or suspicious voice recordings.

It replaces judging a file by its appearance or filename with an analysis result from the connected service, while keeping the exact selected media and processing settings explicit.

media-authenticity — Skill for Claude Code and Codex by resemble-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 resemble-ai/resemble-mcp --skill media-authenticity

Clone the repo

git clone --depth 1 https://github.com/resemble-ai/resemble-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/resemble-ai/resemble-mcp/media-authenticity/github.svg)](https://agentmods.dev/skills/resemble-ai/resemble-mcp/media-authenticity)

Your own site

<a href="https://agentmods.dev/skills/resemble-ai/resemble-mcp/media-authenticity"><img src="https://agentmods.dev/badge/skills/resemble-ai/resemble-mcp/media-authenticity/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/resemble-ai/resemble-mcp/media-authenticity"><img src="https://agentmods.dev/badge/skills/resemble-ai/resemble-mcp/media-authenticity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 707 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.

Model	Per session	Once invoked
Fable 5.1	$0.00054	$0.00707
Opus 5.5	$0.00022	$0.00283
Sonnet 5.5	$0.00011	$0.00141
Haiku 4.5	$0.00005	$0.00071

Measured 11d ago against content hash 18a90c22b649, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

media-authenticity 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 11d 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.

copilot/appPackage/skills/media-authenticity/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Media authenticity

Analyze the exact media the user selects using the Resemble connector. Never decide authenticity from appearance, a filename, or your own impression.

Identify the user's media link or selected workspace attachment. If several unrelated files are available and the target is unclear, ask which to analyze. Do not sweep a mailbox, drive, or conversation for extra files.
Use the connected Resemble account. If connection is missing, direct the user to connect the plugin through OAuth. Never request or handle an API key in chat.
Tell the user that selected content is sent to Resemble for analysis and may consume credits. Honor Copilot's tool confirmations. When the user requests private processing, set zero_retention_mode: true; if the account rejects it, report the limitation and do not silently submit without that setting.
Call submit_media_detection once. For a URL, supply url. For a workspace attachment, use Cowork's direct_attachment_file_paths mapping for the tool's file input and provide its original filename. Never manually base64-encode content, fabricate a URL, or publish the file to an external host. Files are limited to 10 MiB; larger inputs need a suitable user-provided HTTPS URL or a smaller file.
Set intelligence: true only when contextual analysis or a transcript is requested. Set audio_source_tracing: true only for an audio-source question. These are additional analyses, not proof of origin or identity.
Retain the returned UUID and call get_media_detection with it. If pending or processing, wait 2 seconds, then 5 seconds, then 10 seconds between reads. Stop at completion or failure. After roughly five minutes, report the job as still processing and give its UUID so it can be resumed. Do not create another job to poll.
Report an authenticity assessment only for status: completed, and only for modalities with actual returned metrics. Preserve zero scores. Present separate audio, image, and video labels when available; do not collapse conflicting signals into one verdict. Never invent a missing score or average scores across modalities.

Read the full file on GitHub · 33 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.

references/result-handling.md 1.6 KB

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.

11d ago First seen · 33 lines · 54 tokens per session scan A 18a90c22b649

Subscribe to this mod's changes

media-authenticity is a skill published in the GitHub repository resemble-ai/resemble-mcp (2 stars, last pushed 11d ago), licensed MIT. It adds 54 tokens to every session and 707 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-28.

Creative and media

media-authenticity next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
media-authenticityresemble-ai/resemble-mcp	Skill	2	11d ago	MIT	A	54	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code