adrkit

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.

Security

Grade A, and why

adrkit 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.

packages/adapters/agent-plugin/.claude-plugin/plugin.json · 25 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "adrkit",
  "displayName": "adrkit — decision memory",
  "version": "0.2.0",
  "description": "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.",
  "author": {
    "name": "Mark Beacom",
    "url": "https://github.com/mbeacom"
  },
  "homepage": "https://adrkit.dev",
  "repository": "https://github.com/mbeacom/adrkit",
  "license": "Apache-2.0",
  "keywords": [
    "adr",
    "architecture-decision-records",
    "decision-memory",
    "decision-backfill",
    "architecture",
    "governance",
    "claude-code",
    "github-copilot"
  ]
}

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.

Related

Other plugins, from other repositories