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/saadshahd/moo.mdWrote 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/saadshahd/moo.md/hold)<a href="https://agentmods.dev/plugins/saadshahd/moo.md/hold"><img src="https://agentmods.dev/badge/plugins/saadshahd/moo.md/hold/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/saadshahd/moo.md/hold"><img src="https://agentmods.dev/badge/plugins/saadshahd/moo.md/hold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
hold 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 yesterday.
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": "hold",
"version": "0.0.1",
"description": "Comprehension at the human's pace. Grasp a change, drive a behavior, land one thing in an audience — until you can say how it works with the agent out of the room.",
"keywords": ["learn", "grasp", "toy", "land", "comprehension"],
"author": {
"name": "Saad Shahd",
"url": "https://saadshahd.github.io"
}
}
What it installs
The manifest is a name and a version. 4 skills travel with it, and installing the plugin installs all of them — 137 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.
- yesterday First seen · 11 lines scan A aeefe8d5abe0
hold is a plugin published in the GitHub repository saadshahd/moo.md (34 stars, last pushed 2d ago), 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 2026-09-07.
Other plugins, from other repositories
daily
Day-to-day skills with memory: a morning briefing, a tutor that remembers what you got wrong, and a retro that turns agent mistakes into one-line fixes.
codex-bridge
Bridge OpenAI Codex CLI into Claude Code for cross-model review, verification, task delegation and collaborative generation.
lark
A plugin for operating Feishu/Lark workplace services such as messages, documents, spreadsheets, calendars, files, tasks, and meetings through a local command-line tool.
second-brain
Agentic workflow with memory and tribal knowledge. Transforms Claude from goldfish to elephant with persistent knowledge across sessions.
chat-saver
Save, search, manage, and export Claude Code conversations to documents or external platforms.
skill-extractor
Extract reusable skills, commands, and agents from conversation history.