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 latestaiagents/agent-skillsnpx agentmods add plugins/latestaiagents/agent-skills/agent-architectgit clone --depth 1 https://github.com/latestaiagents/agent-skillsGrade A, and why
agent-architect 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 3d 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": "agent-architect",
"version": "1.0.0",
"description": "Complete multi-agent systems toolkit: LangGraph workflows, agent orchestration patterns, supervisor hierarchies, human-in-the-loop, A2A protocols, memory systems, and production deployment.",
"author": {
"name": "latestaiagents",
"email": "[email protected]"
},
"homepage": "https://github.com/latestaiagents/agent-skills",
"repository": "https://github.com/latestaiagents/agent-skills",
"license": "MIT",
"keywords": [
"multi-agent",
"langgraph",
"agent-orchestration",
"supervisor-pattern",
"human-in-loop",
"a2a",
"agent-memory",
"llm-agents",
"agentic-ai",
"workflow-automation"
],
"category": "AI/ML Engineering",
"skills": "./skills",
"commands": "./commands",
"mcp": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 13 skills, 1 command, 5 MCP servers travel with it, and installing the plugin installs all of them — 778 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill agent-error-recovery A 53 tokens
- Skill a2a-protocols A 75 tokens
- Skill agent-checkpointing A 67 tokens
- Skill agent-cost-budgeting A 49 tokens
- Skill agent-handoff-protocols A 54 tokens
- Skill agent-memory-systems A 51 tokens
- Skill agent-mesh-architecture A 49 tokens
- Skill agent-testing-harness A 51 tokens
- Skill agent-tool-routing A 53 tokens
- Skill durable-state-patterns A 71 tokens
- Skill langgraph-workflows A 73 tokens
- Skill agent-supervisor-pattern A 55 tokens
- Skill human-in-loop-agents A 69 tokens
- Command debug-agent A 8 tokens
- MCP server langsmith A not measured
- MCP server openai A not measured
- MCP server postgres A not measured
- MCP server redis A not measured
- MCP server slack A not measured
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.
- 3d ago First seen · 29 lines scan A 84964712cde3
agent-architect is a plugin published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo 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.
Other plugins, from other repositories
freshworks-dev-tools
Freshworks Platform 3.0 developer toolkit: FDK setup, app development, AI Actions, app review, and marketplace publish via MCP. API key from https://developers.freshworks.com/developer/ - API key for Freddy AI Copilot for VS Code plugin & Agentic Developer Toolkit. or Connect to Developer MCP server (For MCP…
fw-ai-actions-app
AI Actions and third-party integrations on Platform 3.0: actions.json, SMI, request templates, schemas, validation, and integration workflows.
fw-app-dev
Expert-level skill for building, debugging, reviewing, and migrating Freshworks Platform 3.0 custom apps.
fw-publish
Publish Platform 3.0 custom apps to the Freshworks Marketplace using MCP tools (validate, pack, app-upload, submit/update).
fw-review
Automated Freshworks custom app review: iparams, frontend, deterministic script checks, security, and structured report output.
fw-setup
Install, upgrade, downgrade, and uninstall the Freshworks Development Kit (FDK) with Node.js via nvm (macOS, Windows, Linux).