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 einvoice-dev1/archsteernpx agentmods add plugins/einvoice-dev1/archsteer/marketplacegit clone --depth 1 https://github.com/einvoice-dev1/archsteerGrade A, and why
archsteer 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": "archsteer",
"owner": {
"name": "ArchSteer",
"url": "https://www.archsteer.com"
},
"metadata": {
"description": "Official ArchSteer plugin marketplace — architecture governance for AI coding agents."
},
"plugins": [
{
"name": "archsteer",
"source": "./",
"description": "Architecture governance for AI coding agents — derive the real architecture from any repo, enforce declared rules with a net-new ratchet, and stop agents drifting off pattern before code ships.",
"version": "0.10.0",
"author": {
"name": "ArchSteer",
"url": "https://www.archsteer.com"
},
"homepage": "https://www.archsteer.com",
"repository": "https://github.com/einvoice-dev1/archsteer",
"license": "MIT",
"category": "development",
"keywords": [
"architecture",
"governance",
"conformance",
"code-quality",
"mcp",
"ai-agents",
"nextjs",
"java",
"salesforce",
"security"
]
}
]
}
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.
- yesterday First seen · 39 lines scan A 6e84925a018d
archsteer is a plugin published in the GitHub repository einvoice-dev1/archsteer (5 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.
Other plugins, from other repositories
adrkit
Plugin marketplace listing 1 plugin: adrkit.
adrkit
Load the architecture decisions governing a change, check plans against them, audit existing code and documentation for missing decisions, and draft new records deliberately — driven by the adr CLI.
ai-software-architect
Plugin marketplace listing 1 plugin: ai-software-architect.
ai-software-architect
AI-powered architecture documentation framework with ADRs, reviews, and pragmatic mode.
vibeframe
A control plane for agentic coding: a living, in-repo model of intent, architecture, and code — deterministically indexed, bidirectionally linked, continuously drift-checked. Bundles the VibeFrame MCP server, deterministic hooks, and workflow commands.
vibeframe
Plugin marketplace listing 1 plugin: vibeframe.