A checklist for reviewing Architecture Decision Records, written documents that explain important technical choices and their reasoning. It checks their structure, project conventions, decision quality, and implementation details.

Use it to review one ADR, every ADR in a project, or a proposed ADR taken from an issue.

It helps find missing context, unsupported decisions, and documentation that does not follow the project’s standards.

review-adr — Skill for Claude Code and Codex by rust-works: A checklist for reviewing Architecture Decision Records, written documents…

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.

agentmods

npx agentmods add skills/rust-works/succinctly/review-adr

Any agent

npx skills add rust-works/succinctly --skill review-adr

Clone the repo

git clone --depth 1 https://github.com/rust-works/succinctly

Made for: Claude Code, Codex.

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/skills/rust-works/succinctly/review-adr.svg)](https://agentmods.dev/skills/rust-works/succinctly/review-adr)

Your own site

<a href="https://agentmods.dev/skills/rust-works/succinctly/review-adr"><img src="https://agentmods.dev/badge/skills/rust-works/succinctly/review-adr.svg" alt="Measured on agentmods" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,700 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.02700
Opus 5	$0.00032	$0.01350
Sonnet 5	$0.00013	$0.00540
Haiku 4.5	$0.00006	$0.00270

Measured 5d ago against content hash 6c441698f2e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

review-adr 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 5d 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/skills/review-adr/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR Review Skill

Review one or more Architecture Decision Records (ADRs) across four dimensions: structural accuracy, project conformance, decision quality, and implementation quality.

Step 0: Determine What to Review

Parse $ARGUMENTS to determine the review mode:

Argument	Action
A number (`5`, `05`, `0005`)	Review `docs/adrs/adr-NNNN.md` in the current project
A filename or path	Review that specific ADR file
`all`	Review every `adr-*.md` in `docs/adrs/`
`issue` or a GitHub issue URL	Review a proposed ADR pasted or fetched from the issue
No argument or an ADR in the chat	Ask the user what to review, or use the ADR already in context

If the argument is a GitHub issue URL, use gh issue view <number> --repo <owner/repo> to fetch the issue body, then extract the ADR text from it.

Step 1: Load the ADR Standard

Read the project's foundational ADR to understand the expected format and conventions:

Look for docs/adrs/adr-0000.md in the current working directory.
If found, read it — it is the project's authoritative definition of ADR structure, purpose, naming, and storage conventions.
If not found, fall back to the Michael Nygard baseline:
- Title — short noun phrase, ADR-NNNN: <title>
- Status — one of Proposed / Accepted / Deprecated / Superseded
- Context — the forces at play; why a decision was needed
- Decision — active voice ("We will ..."); the response to those forces
- Consequences — positive, negative, and neutral outcomes
- Stored in version control alongside the code; one decision per record; 1–2 pages

Step 2: Load the ADR(s) to Review

Read the full file on GitHub · 249 lines

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.

5d ago First seen · 249 lines · 64 tokens per session scan A 6c441698f2e9

Subscribe to this mod's changes

review-adr is a skill published in the GitHub repository rust-works/succinctly (52 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 2,700 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-30.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens