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 aicolormedia-dev/dir-treatment --skill treatmentgit clone --depth 1 https://github.com/aicolormedia-dev/dir-treatmentWrote 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/aicolormedia-dev/dir-treatment/treatment)<a href="https://agentmods.dev/skills/aicolormedia-dev/dir-treatment/treatment"><img src="https://agentmods.dev/badge/skills/aicolormedia-dev/dir-treatment/treatment/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/aicolormedia-dev/dir-treatment/treatment"><img src="https://agentmods.dev/badge/skills/aicolormedia-dev/dir-treatment/treatment.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 | $0.00314 | $0.02041 |
| Opus 5 | $0.00157 | $0.01020 |
| Sonnet 5 | $0.00063 | $0.00408 |
| Haiku 4.5 | $0.00031 | $0.00204 |
Grade A, and why
treatment 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 8d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TREATMENT ARCHITECTURE — Orchestrator (v1.3, generate-first)
Skill này gói trọn quy trình dựng hồ sơ Treatment đạo diễn của ColorMedia và thêm lớp tự động tạo asset: từ kịch bản đã chốt → ra 1 file Canva + 1 file PPTX gần hoàn chỉnh, người dùng chỉ QC & update.
Câu chốt: Khách không mua kịch bản — khách mua niềm tin rằng phim sẽ ra đúng như họ hình dung. Treatment bán niềm tin đó bằng cái khách THẤY, NGHE và CẢM.
Đặc tả đầy đủ ở references/treatment_architecture_v1_3.md — ĐỌC FILE ĐÓ TRƯỚC KHI
LÀM (ma trận section × tầng, chi tiết từng khối craft, công thức prompt, template
pptxgenjs, QC checklist, chunks). SKILL.md này chỉ là bản vận hành rút gọn.
Ranh giới trung thực (đọc trước, KHÔNG được vi phạm)
- KHÔNG bịa insight / big idea / credentials / số liệu / giải thưởng. Thiếu → DỪNG,
hỏi; hoặc để placeholder field. Insight/Big Idea kéo từ
insight-first+ kịch bản đã chốt, không tự sinh. - Asset tự tạo (ảnh ChatGPT Image 2, nhạc Suno) là bản định hướng — dán nhãn "AI-generated — chờ QC" (ảnh) và "nhạc demo định hướng" (Suno). Không tuyên bố là cảnh quay/sản phẩm thật. Reference đi mượn phải ghi nguồn + nhãn "REFERENCE".
- Stillomatic/animatic giữ disclaimer: "bản dựng chỉ mang tính hình dung không khí & tiết tấu, chưa phải hình quay thực tế".
- Mọi giả định (màu suy ra, ref suy ra) đánh cờ "đề xuất, chờ duyệt".
Generate-first + Fallback (cốt lõi v1.3)
Agent chủ động tạo asset thật khi động cơ sẵn; khi không sẵn/thất bại → fallback về cơ chế placeholder + prompt ẩn + field/QR (v1.2) và báo rõ asset nào auto, asset nào người dùng tự làm. Tiền điều kiện từng động cơ:
| Asset | Công cụ | Cần có | Fallback |
|---|---|---|---|
| Ảnh reference/keyvisual/storyboard | ChatGPT Image 2 qua Claude-in-Chrome | Extension kết nối + tab ChatGPT (Plus, Image 2) đăng nhập | prompt ẩn + placeholder |
| Reference góc máy/chuyển động/palette | WebSearch + WebFetch + Chrome | Mạng | field link + QR |
| Nhạc | Suno qua Claude-in-Chrome | tab Suno đăng nhập | mô tả hướng + field track |
| File Canva | Canva MCP | MCP Canva uỷ quyền | outline spec để paste |
| File PPTX | pptxgenjs | — | luôn dựng được |
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.
- 8d ago First seen · 104 lines · 314 tokens per session scan A 057bf9bf1ae9
treatment is a skill published in the GitHub repository aicolormedia-dev/dir-treatment (2 stars, last pushed 2mo ago), licensed MIT. It adds 314 tokens to every session and 2,041 once invoked, about $0.0016 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
higgsfield-cinema
Guides users through professional filmmaking workflows in Higgsfield Cinema Studio, including creating multi-shot sequences, configuring optical stacks, applying color grading, managing Soul Cast AI actors, and structuring per-scene prompts with Director Panel camera movements. Use when the user mentions Cinema…
higgsfield-seedance
Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a…
higgsfield-pipeline
Use when the user wants to create a complete multi-shot video, asks how to chain Higgsfield tools together, wants to build a short film or branded content series, asks "what's the full workflow", needs to connect Popcorn → image → video → Recast → audio → assembly, or wants to understand how the platform works as a…
higgsfield-soul
Creates and manages reusable character profiles (Soul IDs) for consistent facial and stylistic identity across multiple image and video generations. Provides identity-vs-motion prompt separation, character sheet creation workflows, micro-expression direction, and Soul Cast AI actor configuration. Use when the user…
higgsfield-acting
Writes the character-performance layer of a video prompt as behavior under pressure, not displayed emotion — objective, obstacle, tactics, beats, subtext, listening, body/status/proxemics, and mandatory eye life. Produces a reusable 150–220-word acting master profile per character plus a per-scene rewrite of it, and a…
higgsfield-audio
Use when the user asks about audio in Higgsfield videos, needs to add dialogue or lip-sync, wants sound effects or ambient sound in generated video, asks about music or BGM in output, or is using any audio-capable model (Kling 3.0, Seedance 1.5 Pro, Seedance 2.0, Veo 3/3.1, Grok Imagine Video). Also use when the…