adr

A command for writing and critically reviewing an architecture decision record (ADR), a document that explains an important software-design choice.

In plain words
What is it for?
Use it to compare design options, challenge failure modes and distributed-system risks, revise the decision, and reach an approve, revise, or reject verdict.
Why use it?
It makes the trade-offs and weak assumptions behind a design visible before the decision is approved.

Command for Claude Code

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 commands/caiaffa/claude-code-ultimate-engineering-system/adr
Clone the repo
git clone --depth 1 https://github.com/caiaffa/claude-code-ultimate-engineering-system

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 191 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 $0.00009 $0.00191
Opus 5 $0.00005 $0.00096
Sonnet 5 $0.00002 $0.00038
Haiku 4.5 $0.00001 $0.00019

Measured 2d ago against content hash 572f674807ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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/commands/adr.md · 26 lines

What it actually says

Phase 1: Draft ADR (principal-engineer)

Use the principal-engineer agent to:

  • Analyze: $ARGUMENTS
  • Draft ADR using ADR_TEMPLATE.md
  • Include at least 2 real options with honest trade-offs

Phase 2: Challenge (parallel)

Run in parallel:

Subagent A — architecture-challenger:

  • Attack the ADR: weakest assumptions, failure modes, alternatives dismissed too quickly

Subagent B — distributed-systems-skeptic (principal-engineer):

  • If the design is distributed: challenge ordering, duplication, partial failure, compensation

Phase 3: Revise + Approve (sequential)

Use the principal-engineer agent to:

  • Incorporate challenge findings
  • Produce final ADR
  • Validate against ADR_REVIEW_CHECKLIST.md
  • Declare verdict: approve / revise / reject
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. 2d ago First seen · 26 lines · 9 tokens per session scan A 572f674807ee

Subscribe to this mod's changes

adr is a command published in the GitHub repository caiaffa/claude-code-ultimate-engineering-system (17 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 191 once invoked, about $0.0000 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.