adr-writing

adr-writing is a skill for Claude Code, Codex from orlando-japan/claude-code-setting. It costs 29 tokens per session (1,046 once invoked), scanned A, original, MIT.

A guide for writing Architecture Decision Records, short documents that capture an important technical choice, its reason and the alternatives rejected. They preserve the context behind decisions for future engineers.

In plain words
What is it for?
Use it when choosing between substantial technical options, such as one database over another, and when the decision has lasting consequences.
Why use it?
It prevents teams from having to rediscover why a difficult-to-reverse architecture choice was made.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when choosing between substantial technical options, such as one database over another, and when the decision has lasting consequences.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orlando-japan/claude-code-setting/adr-writing
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 orlando-japan/claude-code-setting --skill adr-writing
Clone the repo
git clone --depth 1 https://github.com/orlando-japan/claude-code-setting

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.

agentmods badge for adr-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/adr-writing/github.svg)](https://agentmods.dev/skills/orlando-japan/claude-code-setting/adr-writing)
Your own site
<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/adr-writing"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/adr-writing/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-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/adr-writing"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/adr-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,046 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.
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 $0.00029 $0.01046
Opus 5 $0.00015 $0.00523
Sonnet 5 $0.00006 $0.00209
Haiku 4.5 $0.00003 $0.00105

Measured 9d ago against content hash b5511739bf50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

adr-writing 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 9d 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.

templates/extra/skills/adr-writing/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR writing

An ADR captures a decision, the reason, and the alternatives rejected — so that in six months, the "why the hell did we do it this way" question has a one-page answer.

ADRs are not design docs. A design doc is 10+ pages describing how. An ADR is one page describing what we decided and why.

When to write one

  • You chose between two or more real options.
  • The choice has lasting consequences (hard to reverse).
  • The reasoning includes constraints a future reader wouldn't infer from the code.
  • Anyone asked "why don't we do it the other way?"

Not every decision warrants an ADR. "We named the variable x" does not. "We chose Postgres over DynamoDB for the orders service" does.

Template

# ADR-0042: Use Postgres for the orders service

Date: 2026-04-14
Status: Accepted
Deciders: @alice, @bob
Related: ADR-0039 (orders service scope)

## Context

<2-3 paragraphs. What's the problem? What constraints apply?
What are we trying to optimize for? What are the non-goals?>

## Decision

<1 paragraph. Just the decision, no reasoning yet. "We will use
Postgres as the primary database for the orders service.">

## Reasoning

<Why this choice fits the constraints. 3-5 bullets or short
paragraphs. Be concrete — "ACID transactions across orders and
inventory" beats "reliability".>

## Alternatives considered

### Option A: DynamoDB
- Pros: ...
- Cons: ...
- Rejected because: ...

### Option B: MySQL
- Pros: ...
- Cons: ...
- Rejected because: ...

## Consequences

<Both positive and negative. What do we gain? What do we give up?
What will be harder because of this decision?>

## Revisit conditions

<When should someone come back and question this? E.g.,
"If order volume exceeds 10k/sec" or "If we need cross-region
writes".>

Sections that earn their keep

Context

Without context, the decision is inexplicable in 6 months. Include:

  • The problem being solved (not the solution).
  • The constraints (team, budget, deadline, existing systems).
  • The non-goals (what this decision is explicitly not trying to address).

Read the full file on GitHub · 126 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.

  1. 9d ago First seen · 126 lines · 29 tokens per session scan A b5511739bf50

Subscribe to this mod's changes

adr-writing is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 1,046 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

adr-documentation

Architecture Decision Records (ADR) documentation practice. Use when documenting architectural decisions, recording technical trade-offs, creating decision logs, or establishing architectural patterns. Trigger keywords - "ADR", "architecture decision", "decision record", "trade-offs", "architectural decision"…

MadAppGang/claude-code · 60 tokens

architecture-decision-record-creator

Create structured Architecture Decision Records (ADRs) with 7 sections to document architecture decisions with full justification. Use this skill whenever the user has made or needs to make an architecture decision, wants to document why a technical choice was made, is choosing between technologies or patterns, needs…

bookforge-ai/bookforge-skills · 91 tokens

architecture-decision-records

Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes.

GetSkill-Agent/getskill-skills · 41 tokens

documentation-and-adrs

Writes technical documentation and Architecture Decision Records. Use when creating READMEs, API docs, ADRs, or any documentation that needs to explain a system, a decision, or how to use something.

vanja-emichi/a0_agent_skills · 45 tokens

mpm-adr

Architecture Decision Records (ADRs) — opt-in convention for documenting significant, hard-to-reverse architectural decisions using the Nygard template.

bobmatnyc/claude-mpm · 33 tokens

adr-skill

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses…

joelhooks/joelclaw · 89 tokens