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.
/plugin marketplace add atretyak1985/swarmerynpx agentmods add plugins/atretyak1985/swarmery/design-packgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/design-pack)<a href="https://agentmods.dev/plugins/atretyak1985/swarmery/design-pack"><img src="https://agentmods.dev/badge/plugins/atretyak1985/swarmery/design-pack.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
design-pack 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.
What it actually says
{
"name": "design-pack",
"description": "Design-handoff pack: /design-implement turns an exported design (Claude Design HTML export, handoff prompt, or screenshots) into a pixel-accurate implementation in the project's own stack \u2014 token inventory from a real headless render, reuse-vs-create reconnaissance, an approval gate before any code, and a measured pixel diff against the design as the completion criterion. Opt-in; requires core.",
"version": "0.3.1",
"author": {
"name": "atretyak",
"email": "[email protected]"
}
}What it installs
The manifest is a name and a version. 3 skills, 1 command, 1 agent travel with it, and installing the plugin installs all of them — 440 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.
- 2d ago First seen · 9 lines scan A 74b4c75878f6
design-pack is a plugin published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed yesterday), licensed Apache-2.0. 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 2026-09-03.
Other plugins, from other repositories
playgrounds
One-step access to Anthropic's first-party playground plugin: declares the cross-marketplace dependency, routes playground-shaped requests to the upstream skill when it is installed, emits the install commands when it is not, and carries field-tested prompt recipes, cloud-session delivery guidance, and consumer…
frontend-design
Frontend/UI design guidance, gated by scope: a light or surgical change gets inline principles; a wide-sweeping or highly-detailed design gets routed to Claude Design in the browser with a paste-ready design brief.
anvil-pulse
Live operator dashboard for long autonomous anvil runs: claims, phases, lease countdowns, event feed, and stuck-state detection served as a local web page, plus an optional Claude Code statusline segment.
cli-to-plugin
Convert any CLI tool into a self-contained Claude Code plugin by walking its --help tree and generating one skill per command group, plus optional LLM-proposed workflow meta-skills.
fakoli-flow
Intent-driven workflow orchestration — brainstorm, plan, and execute complex projects through coordinated specialist agents with critic gates and evidence-based verification.
gate-router
Deterministic changed-path gate routing: map the files you changed to the verify commands this repo requires before shipping (docs -> strict build, shell -> bash -n, src -> suite), from a per-project rules file instead of session memory.