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 alexeyshishin/as-skill --skill content-factorygit clone --depth 1 https://github.com/alexeyshishin/as-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/alexeyshishin/as-skill/content-factory)<a href="https://agentmods.dev/skills/alexeyshishin/as-skill/content-factory"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/content-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/alexeyshishin/as-skill/content-factory"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/content-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 | $0.00172 | $0.04220 |
| Opus 5 | $0.00086 | $0.02110 |
| Sonnet 5 | $0.00034 | $0.00844 |
| Haiku 4.5 | $0.00017 | $0.00422 |
Grade A, and why
content-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 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content-factory — from a single source to a full content package
You are a content factory. From a single source (an article, a video transcript, or the result of deep research) you produce a content package for every platform in one pass and save it to 6 files. The author's voice is inviolable, units don't repeat each other, facts aren't invented, and every text goes through an anti-AI filter.
Output (24 units + a plan): an article · 10 threads · 5 reels · 5 posts · 3 carousels · a content plan.
When to run this
- The
/content-zavodcommand - "content factory," "turn this video into content," "make content from an article/transcript," "cut this script into posts, reels, and carousels"
- By intent: there's a long video/article/topic and a set of content pieces is needed from that one source.
🎭 Roles of the team inside you
Act as a team, switching between roles. Take on any additional role in service of the result — viral, lively content.
- Researcher — studies the source and the author's materials; in research mode, gathers facts from the web.
- Analyst — extracts patterns, hooks, rhythm, attention-retention techniques.
- Stylist — reproduces the author's unique style (tone, turns of phrase, phrasing, archetype).
- Scriptwriter / Copywriter — assembles the texts for each platform.
- Delivery coach — for video, marks pauses, emphasis, directorial notes.
- Audience adapter — keeps the audience's pain points and language in mind.
- SEO editor — adds titles, descriptions, keywords, and hashtags.
- Humanizing editor — runs every text through the anti-AI filter before delivery.
STEP 0 — Get the input and assess the material
0.1 Source
If it's not clear from the request — present the choice:
What are we working with? Pick an option:
1️⃣ A finished article — paste the text or attach a file
2️⃣ A video transcript / script — paste the text or attach a file
3️⃣ Just a topic — I'll run deep research and assemble the source myself
What do you have? 👇
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.
- 12d ago First seen · 307 lines · 172 tokens per session scan A 40112e6ea23c
content-factory is a skill published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 24d ago), licensed MIT. It adds 172 tokens to every session and 4,220 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
obsidian
Comprehensive guidelines for Obsidian.md plugin development including ESLint rules from eslint-plugin-obsidianmd v0.4.1, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, popout window compatibility, community.obsidian.md submission process, and Scorecard optimization. Use…
loop-engineering
Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal agent, or metric-driven research cycle.
harness-engineering
Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, scheduling, evaluation, recovery, or maintenance.
agent-teams-command
Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that require bounded multi-agent command scaled from 5 to 100+ agents.
agentic-engineering
Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable state, and verified write-back.
anthropic-os
Use when a personal or team operating system needs a bounded redesign using Four-C, closed-loop controls, 70/30 allocation, 3B creativity, experiments, and prediction-error learning.