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 ynishi/mlua-swarmnpx agentmods add plugins/ynishi/mlua-swarm/marketplacegit clone --depth 1 https://github.com/ynishi/mlua-swarmGrade A, and why
mlua-swarm 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": "mlua-swarm",
"owner": {
"name": "Yutaka Nishimura"
},
"description": "Bundled Claude Code plugins for mlua-swarm (mse) — the long-running swarm engine that compiles flow.ir Blueprints and dispatches agent steps to workers.",
"plugins": [
{
"name": "mse",
"source": "./plugins/mse",
"description": "mse Blueprint-authoring DX set (mse-adviser / bp-coder + mse-wake / bp-build skills). Ride the mse MCP server for schema-grounded design and bp_doctor-gated implementation.",
"version": "0.1.0",
"license": "MIT OR Apache-2.0",
"homepage": "https://github.com/ynishi/mlua-swarm",
"repository": "https://github.com/ynishi/mlua-swarm",
"keywords": ["mlua-swarm", "mse", "blueprint", "flow-ir", "agents", "llm"]
}
]
}
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 · 20 lines scan A 180f5010eefa
mlua-swarm is a plugin published in the GitHub repository ynishi/mlua-swarm (1 stars, last pushed 6d 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
soyenriquerocha
Plugin marketplace listing 1 plugin: the-architect.
the-architect
EN: Senior software design consultant. Interviews you about what you want to build, designs the complete architecture, and generates a self-contained blueprint another Claude Code instance can build from autonomously — with acceptance criteria and a verify command on every step. Works on new projects and existing…
claude-code-swarm-plugin
Multi-agent task decomposition and coordination for Claude Code.
claude-plugin
Multi-agent task decomposition and coordination for Claude Code.
swarm-tools
Plugin marketplace listing 1 plugin: swarm.
lua-lsp
Lua language server plugin for Claude Code with lua-language-server integration and automated hooks for linting and formatting.