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 string-os/stringnpx agentmods add plugins/string-os/string/marketplacegit clone --depth 1 https://github.com/string-os/stringGrade A, and why
string-os 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": "string-os",
"owner": {
"name": "string-os",
"url": "https://github.com/string-os"
},
"metadata": {
"description": "String — a universal surface for AI agent work. String apps, web pages, and shell sessions through one MCP tool.",
"version": "0.1.15"
},
"plugins": [
{
"name": "string",
"source": "./",
"description": "The String runtime as a Claude Code plugin. Installs the `string` MCP server (via npx — no manual install) and a skill that walks Claude through installing apps, calling actions, browsing pages as markdown, and recovering from errors.",
"version": "0.1.15",
"author": {
"name": "H1R AI",
"url": "https://h1r.ai"
},
"homepage": "https://string-os.org",
"license": "MIT",
"keywords": ["mcp", "sfmd", "markdown", "agent", "runtime", "apps"],
"category": "workflow"
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 28 lines scan A d226f67db963
string-os is a plugin published in the GitHub repository string-os/string (65 stars, last pushed 13d 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 2026-08-30.
Other plugins, from other repositories
anolisa-tokenless
ANOLISA local marketplace — bundles the Token-Less plugin for Claude Code.
dashclaw
DashClaw governance, integration, troubleshooting, and platform intelligence for Claude Code.
dashclaw
Plugin marketplace listing 1 plugin: dashclaw.
kdcube-builder
Build KDCube bundles and run local KDCube development flows from Claude Code.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
nextjs
Official Claude Code plugin marketplace for Next.js, serving the skills that ship in the vercel/next.js repository.