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 tody-agent/affiliate-product --skill verified-koc-videofactorygit clone --depth 1 https://github.com/tody-agent/affiliate-productWrote 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/tody-agent/affiliate-product/verified-koc-videofactory)<a href="https://agentmods.dev/skills/tody-agent/affiliate-product/verified-koc-videofactory"><img src="https://agentmods.dev/badge/skills/tody-agent/affiliate-product/verified-koc-videofactory/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/tody-agent/affiliate-product/verified-koc-videofactory"><img src="https://agentmods.dev/badge/skills/tody-agent/affiliate-product/verified-koc-videofactory.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 | $0.00093 | $0.01305 |
| Opus 5 | $0.00046 | $0.00652 |
| Sonnet 5 | $0.00019 | $0.00261 |
| Haiku 4.5 | $0.00009 | $0.00130 |
Grade A, and why
verified-koc-videofactory 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verified KOC VideoFactory
Skill này có hai chế độ tách biệt: nghiên cứu và sản xuất. Không dùng research
queue để viết kịch bản; chỉ video PUBLISHED trong verified DB mới được mở khóa
pattern sản xuất.
1. Nghiên cứu bằng Browser MCP
- Dùng Browser MCP trên phiên FastMoss đã đăng nhập; không dùng Computer Use, trình duyệt Playwright riêng, cookie hoặc token do người dùng cung cấp.
- Tuyển creator theo
references/persona-and-browser.md. - Lưu URL TikTok canonical, ID 19 chữ số, caption gốc, snapshot đơn/GMV, kỳ đo, thời điểm và tệp bằng chứng. Không suy đoán format từ caption.
- Nếu TikTok/FastMoss không phát media, gặp CAPTCHA/WAF hoặc mất phiên, ghi trạng thái block chính xác và dừng batch đó. Không viết transcript, CRO hay kịch bản thay thế.
- Có thể kiểm tra queue mà không mở khóa sản xuất:
python -m afflite.cli creator-intel collect \
--queue data/research_queue/introvert_tech_creator_candidates.json
2. Ingest và phân tích verified
Tiếp tục bằng creator-intel ingest-verified theo manifest thật. Mỗi video phải
có MP4, bằng chứng KOC, bằng chứng gắn sản phẩm/giỏ hàng và snapshot commerce.
FFmpeg/STT/CRO phải dẫn về media thật; thiếu media thì giữ BLOCKED_MEDIA.
Không chạy các luồng legacy creator-intel seed, creator-intel script,
creator-storyboard hoặc afflite make-video cho kho verified vì các luồng đó
không bảo đảm provenance.
3. Chọn pattern đủ điều kiện
python -m afflite.cli creator-intel list-patterns \
--verified-db data/verified_creator_intelligence.db \
--niche Tech
Chỉ dùng pattern được lệnh này trả về: ít nhất 5 video PUBLISHED thuộc ít nhất
3 KOC, cùng niche và cùng hook archetype. Nếu danh sách rỗng, báo thiếu bằng
chứng và không tạo kịch bản.
4. Soạn brief có provenance
Đọc references/provenance-contract.md trước khi viết brief. Dùng schema
schemas/evidence-videofactory-brief.schema.json.
- Chọn
FACELESS_VOICEOVERcho cảnh quay tay/sản phẩm/setup và voice profileAdam; chọnLOW_FACE_VLOGcho vlog đời thường ít phụ thuộc nói trực diện. - Lời thoại mới phải ghi
AI_ADAPTED_FROM_VERIFIED_PATTERN; không mạo nhận là transcript của KOC. - Mỗi cảnh dẫn ít nhất một transcript, analysis hoặc keyframe thật bằng Video ID và timestamp.
- Mọi claim sản phẩm lấy từ tệp nguồn cục bộ có SHA-256. Mọi số liệu trong lời
thoại/subtitle phải khai báo
claim_keys; CTA cũng phải dẫn fact. - Không dùng GMV, đơn hàng hay view của KOC làm claim bán hàng cho sản phẩm mới.
What ships with it
4 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.
- 11d ago First seen · 93 lines · 93 tokens per session scan A c0e0158b5a90
verified-koc-videofactory is a skill published in the GitHub repository tody-agent/affiliate-product (0 stars, last pushed 16d ago), licensed MIT. It adds 93 tokens to every session and 1,305 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…