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 anbeime/skill --skill media-processorgit clone --depth 1 https://github.com/anbeime/skillWrote 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/anbeime/skill/media-processor)<a href="https://agentmods.dev/skills/anbeime/skill/media-processor"><img src="https://agentmods.dev/badge/skills/anbeime/skill/media-processor/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/anbeime/skill/media-processor"><img src="https://agentmods.dev/badge/skills/anbeime/skill/media-processor.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 | $0.00072 | $0.01357 |
| Opus 5.5 | $0.00029 | $0.00543 |
| Sonnet 5.5 | $0.00014 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
media-processor 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 1mo 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
8 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.
- references/ffmpeg_guide.md 5.1 KB
- references/imagemagick_guide.md 6.9 KB
- scripts/image_compress.py 2.7 KB runs code
- scripts/image_convert.py 2.7 KB runs code
- scripts/image_scale.py 3.0 KB runs code
- scripts/video_compress.py 2.8 KB runs code
- scripts/video_convert.py 2.5 KB runs code
- scripts/video_scale.py 2.8 KB runs code
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.
- 1mo ago First seen · 146 lines · 72 tokens per session scan A d8760adf86b3
media-processor is a skill published in the GitHub repository anbeime/skill (8,229 stars, last pushed today), with no licence file. It adds 72 tokens to every session and 1,357 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
loop-engineer
Domain-agnostic autonomous loop for any goal — coding, research, content, data, automation, or any objective. Asks 3 questions, then orchestrates a self-assembling agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) that researches, discovers resources, builds…
loop-engineer
Domain-agnostic autonomous loop for any goal — coding, research, content, data, automation, or any objective. Asks 3 questions, then orchestrates a self-assembling agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) that researches, discovers resources, builds…
loop-engineer
Loop engineering wizard for Antigravity. Asks 3 questions, then orchestrates a fully autonomous parallel agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) until the goal is met. Uses invokesubagent for true parallel dispatch. Researcher agents use the built-in…
loop-engineer
Domain-agnostic autonomous loop for OpenAI Codex CLI. Asks 3 questions, scaffolds a parallel agent team as TOML files (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper), generates loop-stack/ / state files, and outputs the exact codex /goal command for the fully autonomous…
loop-engineer
Loop engineering wizard for Hermes Agent. Asks 3 questions, then orchestrates a fully autonomous parallel agent team (resource-scout, researcher, planner, agent-factory, executor, verifier, auditor, memory-keeper) for any goal. Uses delegatetask for true parallel subagent dispatch. Modes: build (from scratch)…
loop-engineer
Domain-agnostic autonomous loop wizard for VS Code GitHub Copilot. Asks 3 questions, then orchestrates a fully autonomous agent team via true parallel subagent dispatch. Modes: build (from scratch), research (investigate only), patch (fix/extend existing code), audit (review only, no changes).