Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/the-cyber-boardroom/SGraph-AI__App__Sendnpx agentmods add skills/the-cyber-boardroom/sgraph-ai__app__send/create-vault-contentWrote 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/the-cyber-boardroom/sgraph-ai__app__send/create-vault-content)<a href="https://agentmods.dev/skills/the-cyber-boardroom/sgraph-ai__app__send/create-vault-content"><img src="https://agentmods.dev/badge/skills/the-cyber-boardroom/sgraph-ai__app__send/create-vault-content/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/the-cyber-boardroom/sgraph-ai__app__send/create-vault-content"><img src="https://agentmods.dev/badge/skills/the-cyber-boardroom/sgraph-ai__app__send/create-vault-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00160 | $0.06061 |
| Opus 5.5 | $0.00064 | $0.02424 |
| Sonnet 5.5 | $0.00032 | $0.01212 |
| Haiku 4.5 | $0.00016 | $0.00606 |
Grade A, and why
create-vault-content 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 2mo 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 — 702 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Create Vault Content for SG/Send Browse
Overview
The SG/Send Browse view (send.sgraph.ai) decrypts and renders the contents of an encrypted vault in a two-pane layout: file tree on the left, tabbed preview on the right.
You can create two types of rich content in a vault:
_page.json— component-based page layouts (hero, gallery, slides, cards, etc.)- Markdown (
.md) — prose documents with images, links, and tables
This skill gives you the complete reference for both. Use the sgit skill to create, commit, and push to the vault.
Quick decision: _page.json vs Markdown
Use _page.json when |
Use Markdown when |
|---|---|
| You want a designed hero banner | You want prose-first documents |
| Gallery of images / slideshow | Text with inline images |
| Hub page with clickable cards | Linked document hierarchy |
| Multiple distinct layout sections | Article, README, report |
| Investor deck, portfolio page | Working notes, specs |
| Embedded PDF viewer | Step-by-step guide |
| Explicit theme and font control | Quick content with minimal setup |
Both can coexist in the same folder. _page.json takes priority in the Browse view;
markdown files remain as alternatives.
Part 1: _page.json Page Layouts
1.1 File placement
Name the file exactly _page.json in the folder it describes. The Browse view
auto-detects it — no registration needed.
my-vault/
_page.json ← root page
articles/
_page.json ← articles hub
deep-dive/
_page.json ← article page
images/
cover.jpg
Auto-open: if the vault root has _page.json, it renders immediately when the vault
is opened.
1.2 Top-level structure
{
"title": "Page Title",
"theme": { "mode": "dark", "accent": "#00d4aa" },
"navigation": [
{ "label": "Overview", "anchor": "overview" }
],
"components": [
{ "type": "hero", "props": { "title": "..." } }
]
}
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.
- 2mo ago First seen · 702 lines · 160 tokens per session scan A 6e0688854728
create-vault-content is a skill published in the GitHub repository the-cyber-boardroom/SGraph-AI__App__Send (11 stars, last pushed 9d ago), licensed Apache-2.0. It adds 160 tokens to every session and 6,061 once invoked, about $0.0006 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.
create-vault-content compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| create-vault-contentthe-cyber-boardroom/SGraph-AI__App__Send | Skill | 11 | 9d ago | Apache-2.0 | A | 160 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 3d ago | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| ppt-reviewOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 2 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |