A toolkit for creating and maintaining ADRs, which record why a software architecture choice was made.

Use it to start ADRs, write them in different formats, enforce rules, manage their lifecycle, add decision context to agent work, generate decision indexes, and run local health checks.

It keeps design decisions documented, checked, linked, and updated as the project changes.

adr-kit — Plugin for Claude Code by rvdbreemen

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.

Clone the repo

git clone --depth 1 https://github.com/rvdbreemen/adr-kit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/rvdbreemen/adr-kit/adr-kit/github.svg)](https://agentmods.dev/plugins/rvdbreemen/adr-kit/adr-kit)

Your own site

<a href="https://agentmods.dev/plugins/rvdbreemen/adr-kit/adr-kit"><img src="https://agentmods.dev/badge/plugins/rvdbreemen/adr-kit/adr-kit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/rvdbreemen/adr-kit/adr-kit"><img src="https://agentmods.dev/badge/plugins/rvdbreemen/adr-kit/adr-kit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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

When invoked not measured The manifest loads nothing itself; its 17 skills, 1 command, 1 agent, 6 hooks, 1 MCP server cost 385 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

adr-kit 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.

.claude-plugin/plugin.json · 30 lines

What it actually says

{
  "name": "adr-kit",
  "description": "Architecture Decision Record toolkit for AI coding agents: bootstrap, multi-format authoring, bounded deterministic enforcement, lifecycle workflows, context injection, generated graph indexes, and local health checks.",
  "version": "0.61.0",
  "author": {
    "name": "Robert van den Breemen",
    "url": "https://github.com/rvdbreemen"
  },
  "homepage": "https://github.com/rvdbreemen/adr-kit",
  "repository": "https://github.com/rvdbreemen/adr-kit.git",
  "license": "MIT",
  "keywords": [
    "adr",
    "architecture-decision-records",
    "claude-code",
    "github-copilot",
    "codex",
    "agent-skills",
    "ai-coding-assistant",
    "documentation",
    "decision-records",
    "verification-gates",
    "anti-rationalization",
    "lint",
    "guardian",
    "staleness-detection"
  ],
  "dependencies": []
}

Contents

What it installs

The manifest is a name and a version. 17 skills, 1 command, 1 agent, 6 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 385 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.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.

marketplace.json 799 B

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.

3d ago Changed 1f8f80e0a8e6
13d ago Changed 505bd608f1bb
19d ago Changed 53f25d340004
21d ago Changed bd281e46dbc6
1mo ago Changed 3d02c63aca39
1mo ago First seen · 30 lines scan A 7073f46a1fad

Subscribe to this mod's changes

adr-kit is a plugin published in the GitHub repository rvdbreemen/adr-kit (13 stars, last pushed yesterday), 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.

Claude Code Planning adr agent-skills ai-coding-assistant architecture-decision-records codex

adrkit

Load the architecture decisions governing a change, check plans against them, audit existing code and documentation for missing decisions, draft new records deliberately, and (in GitHub Copilot CLI) run an advisory adr-review workflow, and open a read-only decision-review canvas in the GitHub Copilot app — driven by…

mbeacom/adrkit · not measured

docflow

ADR-driven documentation workflow: a bootstrap skill that scaffolds an Architecture Decision Record (ADR) catalogue, a plan/ queue, AGENTS.md conventions, and agent/ coordination — plus lifecycle skills to author ADRs, queue and ship work, add conventions, audit consistency, brainstorm decisions, run agent waves, and.

EvolveHQ/docflow · not measured

actual-cli

Feature-complete companion for the actual CLI — runs and troubleshoots sync, status, auth, config, runners, and models across all 5 runners and 3 output formats, and gates both implementation plans and the diffs agents produce against the ADR rules committed in .actual/rules/.

actual-software/actual-skill · not measured

adr-kit