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.
npx skills add moonlight-lupin/agent-skills --skill media-analyzergit clone --depth 1 https://github.com/moonlight-lupin/agent-skillsWrote 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.
[](https://agentmods.dev/skills/moonlight-lupin/agent-skills/media-analyzer)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/media-analyzer"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/media-analyzer/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.
<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/media-analyzer"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/media-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.03163 |
| Opus 5 | $0.00029 | $0.01581 |
| Sonnet 5 | $0.00012 | $0.00633 |
| Haiku 4.5 | $0.00006 | $0.00316 |
Grade A, and why
media-analyzer 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Analyzer
Overview
Media Analyzer is a technique-focused workflow for reading news articles, opinion pieces, press releases, and other media with a critical but neutral lens. Media texts often use rhetorical choices to shape perception: emotionally charged verbs, selective statistics, source mixes, framing metaphors, omissions, emotional appeals, and disproportionate presentation of evidence. This skill identifies those observable techniques systematically without deciding which political position is correct.
Use this skill when the goal is to understand how a text guides interpretation. Do not use it to label an outlet, author, or article as left-wing, right-wing, conservative, liberal, pro-X, or anti-Y. The output is a structured analysis report that surfaces technique usage and leaves conclusions to the reader.
Core Principle: Detect Techniques, Not Positions
The central rule is: DETECT TECHNIQUES, NOT POSITIONS.
Never label a source as "left-wing," "right-wing," "conservative," "liberal," or "biased toward X." Instead, identify specific rhetorical tools:
- loaded words and their neutral alternatives;
- source types quoted or omitted;
- statistics cited and relevant data not cited;
- framing devices such as metaphor, naming choices, presupposition, or loaded questions;
- emotional appeal patterns;
- false balance between positions with unequal evidence weight.
A valid finding says: "The article uses three high-intensity verbs in the first four paragraphs." An invalid finding says: "The article is biased against the policy." Keep the analysis observable, specific, and politically direction-neutral.
Quick Start
From this skill directory:
python scripts/analyze.py scan --input article.md
Save scan output and generate a report:
python scripts/analyze.py scan --input article.md --output analysis.json
python scripts/analyze.py report --scan analysis.json --output report.md
Review the loaded-language dictionary:
What ships with it
5 files 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.
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.
- 12d ago First seen · 322 lines · 58 tokens per session scan A 3d7e164199dd
media-analyzer is a skill published in the GitHub repository moonlight-lupin/agent-skills (64 stars, last pushed 5d ago), licensed MIT. It adds 58 tokens to every session and 3,163 once invoked, about $0.0003 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.
Other skills, from other repositories
SoloFlow
A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
image
Create or optimize marketing images, social graphics, product mockups, banners, cover art, listing visuals, brand assets, image prompts, WebP files, and OG images.
video
Plan and produce video with available AI tools or programmatic frameworks. Use for video prompts, avatars, explainers, demos, templates, pipelines, and generation.
content-research-writer
Research, outline, draft, cite, and revise articles, reports, tutorials, newsletters, and case studies with traceable sources and preserved voice.
content-analysis
Analyze articles, documents, videos, podcasts, and transcripts for arguments, evidence, themes, assumptions, contradictions, insights, and unanswered questions.