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 somnus0x/agt-skill-pack --skill faceless-factorygit clone --depth 1 https://github.com/somnus0x/agt-skill-packWrote 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/somnus0x/agt-skill-pack/faceless-factory)<a href="https://agentmods.dev/skills/somnus0x/agt-skill-pack/faceless-factory"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/faceless-factory/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/somnus0x/agt-skill-pack/faceless-factory"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/faceless-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.01024 |
| Opus 5.5 | $0.00025 | $0.00410 |
| Sonnet 5.5 | $0.00012 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
faceless-factory 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Faceless Factory — AI Makes Raw Material, Code Assembles
Every time you gen a full carousel with AI, it comes out beautiful one round and broken the next: characters drift, colors shift, Thai fonts shatter into tofu. That's not a prompt problem. It's a job-assignment problem.
The core idea
You're using a tool that guesses every time to do work that needs to be the same every time. Split it into two layers:
- Top layer (expensive, AI-gen): backgrounds, characters, opening clips. These are raw material. Gen once, keep it, reuse it. Randomness is fine — even wanted — here.
- Bottom layer (cheap, code): text, layout, composition, final render to file. Never let AI gen this. Code does it, deterministically, for free.
The insight most people miss: the part everyone thinks they must pay the most for (the gen) is the least important. The part that makes it shippable — the assembly — is plain code that runs for free, identically, forever.
When to use
Say /faceless-factory or: "my AI carousel is inconsistent", "Thai fonts keep breaking", "every gen is a gamble", "how do I make repeatable content with AI", "the faces/colors drift between slides".
Why code, not AI, for the bottom layer
The bottom-layer work — JSON, render scripts, ffmpeg — is "boring but must be exact." It doesn't need imagination. It needs to come out pixel-identical every run, which is exactly what AI gen cannot do and code does for free.
Concrete payoffs once you split:
- Thai text never breaks again — it isn't generated, it's rendered with a real font.
- Gen the background once, render N cards for $0 — no paying again to remake the same thing.
- No more gacha — you stop lucking into a good result.
The two-tool division of labor (agent workflow)
If you drive this with coding agents, split the roles:
- The code-writer agent builds the machine: a render script (PIL for images, ffmpeg for video) that reads one JSON file and draws the deliverable.
- The pipeline-runner agent runs the line: invokes the script, checks the JSON is complete, keeps a manifest so nothing double-renders, and QAs the final 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.
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 · 70 lines · 62 tokens per session scan A 64def90e4edd
faceless-factory is a skill published in the GitHub repository somnus0x/agt-skill-pack (74 stars, last pushed 18d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,024 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…