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/ynishi/mlua-swarmWrote 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/ynishi/mlua-swarm/mse)<a href="https://agentmods.dev/plugins/ynishi/mlua-swarm/mse"><img src="https://agentmods.dev/badge/plugins/ynishi/mlua-swarm/mse/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/ynishi/mlua-swarm/mse"><img src="https://agentmods.dev/badge/plugins/ynishi/mlua-swarm/mse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mse 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 1mo 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": "mse",
"version": "0.1.0",
"description": "mse Blueprint-authoring DX set (mse-adviser / bp-coder + mse-wake / bp-build skills). Bundled with mlua-swarm.",
"author": {
"name": "Yutaka Nishimura"
},
"homepage": "https://github.com/ynishi/mlua-swarm",
"repository": "https://github.com/ynishi/mlua-swarm",
"license": "MIT OR Apache-2.0",
"keywords": ["mlua-swarm", "mse", "blueprint", "flow-ir", "agents", "llm"]
}
What it installs
The manifest is a name and a version. 2 skills, 2 agents travel with it, and installing the plugin installs all of them — 317 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.
- 1mo ago First seen · 13 lines scan A 0e2d386af273
mse is a plugin published in the GitHub repository ynishi/mlua-swarm (1 stars, last pushed 1mo ago), 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 2026-08-31.
Other plugins, from other repositories
bevy-plugin
Bevy game engine development - ECS, rendering, game architecture.
Elpis
Provider-neutral terminal agent shell for controlled context, persistent memory, safe execution, and session continuity.
kin
Kin keeps a living map of the software itself so humans and agents can understand what every change touches. Locate, search, context packs, data-flow tracing, and impact analysis without raw file search.
rustunnel
Expose local services via secure tunnels. Create public HTTPS/TCP/UDP URLs, peer-to-peer tunnels, and load-balanced pools for webhooks, demos, and AI agent workflows.
dd:rust
Rust conventions and best practices for Claude Code.
rust-tools
SOTA Rust tooling - refactoring, profiling, benchmarking, testing, SIMD, dependency audit.