architecture-decision-record

architecture-decision-record is a skill for Claude Code, Codex from affectionatec/agentic-engineering. It costs 119 tokens per session (2,501 once invoked), scanned A, original, MIT.

An architecture decision record, or ADR, is a permanent project note explaining an important technical choice, the alternatives, and what was given up.

In plain words
What is it for?
Use it for choices with several valid options and lasting effects, such as selecting an API style, technology, or repository structure.
Why use it?
It preserves the reasoning behind decisions so people can understand them later, even after the original discussion is forgotten.

Skill for Claude CodeCodex

Part of the agentic-engineering plugin — 12 skills, 2 commands, 1 agent shipped together

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/affectionatec/agentic-engineering/architecture-decision-record
Any agent
npx skills add affectionatec/agentic-engineering --skill architecture-decision-record
Clone the repo
git clone --depth 1 https://github.com/affectionatec/agentic-engineering

Made for: Claude Code, Codex.

Or install agentic-engineering, the plugin that ships this one along with the rest of its 12 skills, 2 commands, 1 agent.

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 architecture-decision-record

README.md
[![agentmods](https://agentmods.dev/badge/skills/affectionatec/agentic-engineering/architecture-decision-record.svg)](https://agentmods.dev/skills/affectionatec/agentic-engineering/architecture-decision-record)
Your own site
<a href="https://agentmods.dev/skills/affectionatec/agentic-engineering/architecture-decision-record"><img src="https://agentmods.dev/badge/skills/affectionatec/agentic-engineering/architecture-decision-record.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,501 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.

ModelPer sessionOnce invoked
Fable 5 $0.00119 $0.02501
Opus 5 $0.00060 $0.01251
Sonnet 5 $0.00024 $0.00500
Haiku 4.5 $0.00012 $0.00250

Measured 4d ago against content hash 196ccc0899e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architecture-decision-record 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 4d 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.

skills/architecture-decision-record/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Decision Record (ADR)

Core constraint: ADRs are append-only. Never edit history — supersede with a new ADR. Write for the reader six months from now with zero context.

Quick Reference

Use when A choice has 2+ valid options with lasting consequences
Skip when Variable names, choices already mandated by an existing ADR, explicitly throwaway prototyping
Output docs/adr/ADR-NNN-[slug].md — one decision per ADR
Sequence PRD / SPEC → ADR → IMPL PLAN
Iron rule Append-only. Never rewrite. Supersede instead.
Sibling skills [[project-kickoff-prd]] · [[technical-specification]] · [[implementation-plan]] · [[status-tracker]] · [[independent-verification]] · [[git-workflow]]

Role

You are a technical decision historian. Your job is to recognize decision forks — moments where multiple valid paths exist — and capture the decision with enough context that any future reader understands not just WHAT was chosen, but WHY, and what was sacrificed.

Persona & Tone

  • Think like a future archaeologist reading this decision in 6 months with no memory of this conversation.
  • Be honest about trade-offs — no decision is universally "best." Say what you gave up.
  • Be concise but complete — a good ADR is one page, not five.
  • Be neutral in tone — describe options fairly, then explain the decision rationale.

When to Create

Proactively create an ADR when:

  • The conversation reaches a fork with 2+ technically valid options (e.g., "REST or GraphQL?", "monorepo or polyrepo?", "PostgreSQL or DynamoDB?")
  • A technology or library choice is made that constrains future options
  • An architectural pattern is chosen (event sourcing, CQRS, microservices, modular monolith)
  • A trade-off is explicitly accepted (e.g., "we'll accept eventual consistency for better write throughput")
  • A constraint is imposed that limits future flexibility (e.g., "single-tenant only for v1")
  • A previous ADR is being reconsidered or overridden

Read the full file on GitHub · 232 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. 4d ago First seen · 232 lines · 119 tokens per session scan A 196ccc0899e5

Subscribe to this mod's changes

architecture-decision-record is a skill published in the GitHub repository affectionatec/agentic-engineering (4 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 2,501 once invoked, about $0.0006 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.