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.
git clone --depth 1 https://github.com/bengous/claude-code-pluginsWrote 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/plugins/bengous/claude-code-plugins/vellum)<a href="https://agentmods.dev/plugins/bengous/claude-code-plugins/vellum"><img src="https://agentmods.dev/badge/plugins/bengous/claude-code-plugins/vellum/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/plugins/bengous/claude-code-plugins/vellum"><img src="https://agentmods.dev/badge/plugins/bengous/claude-code-plugins/vellum.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
vellum 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 4d 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.
What it actually says
{
"name": "vellum",
"version": "0.17.4",
"description": "Plan at the frontiers and review the plan in the browser: decisions and interfaces before mechanics, vertical slices each closed by a check. /vellum:start opens a planning mode of its own: Claude writes the plan and its mockups and grills the reviewer on the open choices; the reviewer comments, edits or approves in a page, and the answer reaches Claude as a prompt.",
"author": {
"name": "Augustin BENGOLEA",
"email": "[email protected]"
},
"homepage": "https://github.com/bengous/claude-code-plugins/tree/main/vellum",
"repository": "https://github.com/bengous/claude-code-plugins",
"license": "MIT",
"keywords": [
"planning",
"browser-review",
"function-hooks",
"plan-mode",
"design",
"interfaces",
"vertical-slices",
"review"
]
}
What it installs
The manifest is a name and a version. 2 skills, 1 agent travel with it, and installing the plugin installs all of them — 243 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 4d ago Changed db11cc55e4e0
- 9d ago Changed bf12d8b91c74
- 14d ago Changed a3484757a4c4
- 17d ago Changed d537952c74ba
- 21d ago Changed 89a57944859e
- 23d ago Changed 5c01dd16ffa5
- 24d ago First seen · 23 lines scan A bdaf3cff8894
vellum is a plugin published in the GitHub repository bengous/claude-code-plugins (5 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-23.
Other plugins, from other repositories
git
Git workflow tools: commits, PRs, review inbox, checkout, and work triage.
aio-visual-diff
Verify AI-built UI against design via measurement-driven diff — extracts computed CSS and bounding boxes through Chrome DevTools MCP, diffs against Figma reference or a frozen baseline, and feeds numerical deltas back to the agent. No screenshot eyeballing.
ui-input-skills
Form systems, search, and filter components for user input and data collection.
hyperstack
Disciplined MCP server + skill system. 16 plugins and 121 tools covering designer (6 personalities, 13 page templates, 9 presets), shadcn/ui, design tokens, ui/ux, React Flow v12, Motion v12, Lenis, React 19, Echo, Go, Rust, product-manager, marketing, reflect, and optimizer. 29 skills with adversarial enforcement…
stark-figma-drive
Exporta frames do Figma e faz upload automatico para o Google Drive do cliente.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.