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 agentmods add skills/anfaia/skillnet/skillnpx skills add ANFAIA/SkillNet --skill skillgit clone --depth 1 https://github.com/ANFAIA/SkillNetWhat 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 | $0.00084 | $0.02233 |
| Opus 5 | $0.00042 | $0.01117 |
| Sonnet 5 | $0.00017 | $0.00447 |
| Haiku 4.5 | $0.00008 | $0.00223 |
Grade A, and why
a2tl-video 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 2d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A2TL-Video (web player)
Use this skill to turn content into an animated explainer. You write a small
.vdsl file (a compact, ~30-100 line spec) and A2TL-Video renders it to a
single, self-contained HTML file that plays instantly in any browser --
auto-fitting stage, play/pause, and a scrub bar, all inline with no build step
and no external assets. There is no MP4 and no video-encoding step: the
deliverable is the web player, which also embeds directly into a page.
A2TL-Video is part of the A2TL (Agent to Transformation Language) family alongside a2tl-web (for web pages).
When to use
- User wants a video/animation about a concept, feature, or process
- User wants to add an animated explainer to documentation, a course, or a landing page
- User says "make a video about…", "animate this", "create an explainer for…"
How to use
- Read the content the user wants to visualize.
- Write a
.vdslfile (see the format below). - Produce the player, either way:
- CLI:
npx vdsl play <file>.vdsl-- writes<file>.htmlnext to it. Open it to play; it embeds anywhere. - MCP tool: call
render_playerwith{ spec, theme?, output? }. It returns the self-contained HTML (and writes a.htmlwhen you passoutput).
- CLI:
- Iterate on the spec and re-render. Do not try to produce an MP4 -- the product is the HTML web player.
Two more MCP tools help you stay accurate:
list_components— the components, viz types, reveals, transitions, positions, accents, fonts, and theme names this build supports.list_icons— the exact icon names valid foricon "<name>".
Document structure
VDSL/1 # required version header, must be the first line
theme dark-tech # base theme (see Themes)
palette ink:"#0b1020" bg:"#f7f7f2" # optional: inline colour overrides
font display:"Georgia" body:"Inter" # optional: inline font overrides
canvas 1920x1080 # optional stage size (default 1920x1080)
scene "<title>" <duration>s <transition>
<component> <args…> <timing>
<component> <args…> <timing>
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.
- 2d ago First seen · 183 lines · 84 tokens per session scan A 8c8e19845bff
a2tl-video is a skill published in the GitHub repository ANFAIA/SkillNet (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 84 tokens to every session and 2,233 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
trellis-start
Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or…
Universal Tracker
Cross-platform background monitor to auto-detect new videos/posts (YouTube, Douyin, Website) and run team workflows.
schema-markup-generator
Generate JSON-LD structured data for FAQ, HowTo, Article, Product, LocalBusiness rich results. Schema标记/结构化数据.
content-gap-analysis
Find content gaps: topics and keywords competitors cover that you don't, with editorial calendar. 内容缺口/选题规划.
ai-strategy-report
Generate comprehensive AI strategy reports (15+ slides) in PowerPoint format. Analyzes company's digital readiness, identifies high-value AI use cases, creates implementation roadmaps, and provides ROI projections. Designed for consulting firm quality deliverables.
sox-compliance-checklist
基于PCAOB AS 2201和SOX Section 302/404，执行萨班斯-奥克斯利法案合规检查，涵盖管理层评估、内部控制评价和审计师鉴证.