adr

adr is a skill for Claude Code from joaquimscosta/arkhe-claude-plugins. It costs 78 tokens per session (2,227 once invoked), scanned A, original, MIT.

Architecture Decision Records (ADRs) are short documents that record important software design choices, including the reasons and alternatives. This add-on creates, reviews, numbers, and indexes ADR files.

In plain words
What is it for?
Use it to create, review, list, update, or replace ADRs, and to regenerate their project index.
Why use it?
It keeps architectural decisions consistent and easy to find as a project changes. It also helps check that decisions explain their reasoning and consequences.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the doc plugin — 3 skills shipped together

Good fit Use it to create, review, list, update, or replace ADRs, and to regenerate their project index.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joaquimscosta/arkhe-claude-plugins/adr
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.

Any agent
npx skills add joaquimscosta/arkhe-claude-plugins --skill adr
Clone the repo
git clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-plugins

Made for: Claude Code.

Or install doc, the plugin that ships this one along with the rest of its 3 skills.

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.

agentmods badge for adr

README.md
[![agentmods](https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/adr/github.svg)](https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/adr)
Your own site
<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/adr"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/adr/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.

agentmods 80×15 button for adr

Your own site · 80×15
<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/adr"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/adr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,227 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.02227
Opus 5 $0.00039 $0.01113
Sonnet 5 $0.00016 $0.00445
Haiku 4.5 $0.00008 $0.00223

Measured 10d ago against content hash 317b4ddd5cb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 10d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/adr_create.py, scripts/adr_index.py, scripts/adr_supersede.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/doc/skills/adr/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR Manager

Create and manage Architecture Decision Records following project conventions with automatic numbering and index maintenance.

Argument Parsing

When invoked explicitly with /adr <action>, parse the first word:

First word Remaining args Operation
create <title> Create a new ADR with the given title
review <path> Lightweight quality review of an ADR
status <number> <status> Transition ADR status with validation and side effects
list (none) List all ADRs (same as running adr_index.py --dry-run)
supersede <old-number> <new-number> Supersede an old ADR with a new one
index (none) Regenerate the README.md index
(empty) Auto-detect from conversation context

If the first word doesn't match an action, treat the entire $ARGUMENTS as a title and default to create.

When auto-invoked (no explicit /adr command), detect the operation from conversation context as before.

Auto-Invoke Triggers

This skill automatically activates when:

  1. Keywords: "ADR", "architecture decision", "document this decision", "record the decision"
  2. Editing ADR files: Files in docs/adr/, doc/adr/, architecture/decisions/, .adr/
  3. Discussing architectural choices: Framework selection, technology decisions, pattern choices

What This Skill Delivers

1. ADR Creation (Enhanced)

  • Gather context from conversation, codebase, and existing ADRs
  • Confirm decision topic with user before drafting
  • Auto-detect project's ADR directory and template style
  • Auto-number ADRs (scan existing, increment)
  • Draft populated ADR with real content (not blank template)
  • Always append Author's Notes section (2-5 items)
  • Offer MADR 4.0 enhancements as optional additions
  • Suggest /adr review <path> after creation

2. Directory Discovery

Search order for ADR directories:

  1. docs/adr/
  2. doc/adr/
  3. architecture/decisions/
  4. .adr/
  5. Create docs/adr/ if none exists

Read the full file on GitHub · 260 lines

Files

What ships with it

6 files beside SKILL.md 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.

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.

  1. 10d ago First seen · 260 lines · 78 tokens per session scan A 317b4ddd5cb6

Subscribe to this mod's changes

adr is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 26d ago), licensed MIT. It adds 78 tokens to every session and 2,227 once invoked, about $0.0004 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.