What is frontier-intelligence-lab?

A plugin for designing AI-agent loops: repeated cycles in which an agent performs work and a verifier checks the result. It can create design documents for a new loop or audit an existing one.

Use it to design or review agent workflows, define their verification rules, and document when a task should not be put in a loop.

It helps decide whether a task should be automated repeatedly and makes the checking step explicit. This can expose unsafe or unreliable loop designs before they are used.

frontier-intelligence-lab — Plugin by Frontier-Intelligence-Lab

Install

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.

Claude Code

/plugin marketplace add Frontier-Intelligence-Lab/loop-architect

agentmods

npx agentmods add plugins/frontier-intelligence-lab/loop-architect/marketplace

Clone the repo

git clone --depth 1 https://github.com/Frontier-Intelligence-Lab/loop-architect

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

frontier-intelligence-lab 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.

.claude-plugin/marketplace.json · 28 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-marketplace.json",
  "name": "frontier-intelligence-lab",
  "description": "Skills for designing safe, verifier-first AI agent loops.",
  "version": "0.1.0",
  "owner": {
    "name": "Frontier Intelligence Lab"
  },
  "plugins": [
    {
      "name": "loop-architect",
      "source": "./",
      "description": "Verifier-first skill for designing safe AI agent loops — or refusing when a task should not be looped. Produces a LOOP.md + VERIFIER.md, an AUDIT.md for an existing loop, or a reasoned refusal.",
      "version": "0.1.0",
      "author": {
        "name": "Frontier Intelligence Lab"
      },
      "homepage": "https://github.com/Frontier-Intelligence-Lab/loop-architect",
      "repository": "https://github.com/Frontier-Intelligence-Lab/loop-architect",
      "license": "MIT",
      "category": "development",
      "keywords": ["agent-loops", "verifier", "automation", "ai-agents", "safety"],
      "tags": ["agent-loops", "verifier", "automation", "ai-agents", "safety"],
      "skills": "./skills"
    }
  ]
}

Changes

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 · 28 lines scan A 20f35b358f87

Subscribe to this mod's changes

frontier-intelligence-lab is a plugin published in the GitHub repository Frontier-Intelligence-Lab/loop-architect (4 stars, last pushed 1mo 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 2026-08-31.

Code review Data and AI Documents LLM agent-loops agent-skills ai-agents automation claude-code

frontier-intelligence-lab

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

thanos

thanos

nextjs

nextjs

claude-plugins-official

knowledge-work-plugins