create-adr

A command that creates an Architecture Decision Record, a short document explaining an important technical choice and its context. It records the decision and its expected consequences for future developers.

In plain words
What is it for?
Documenting why a system uses a particular design, technology, constraint, or trade-off, while checking whether the project already has an ADR format.
Why use it?
It preserves the reasoning behind architectural choices, so later changes do not depend only on oral knowledge or guesswork.

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/wbern/agent-instructions/create-adr
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

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 1,730 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 $0.01730
Opus 5 $0.00005 $0.00865
Sonnet 5 $0.00002 $0.00346
Haiku 4.5 $0.00001 $0.00173

Measured 2d ago against content hash f532b9ea2002, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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/create-adr.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create ADR: Architecture Decision Record Creator

Create a new ADR to document an architectural decision. ADRs capture the "why" behind technical choices, helping future developers understand constraints and tradeoffs.

ADRs were introduced by Michael Nygard in 2011. The core structure (Context, Decision, Consequences) remains the standard.

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

Plan File Restriction

NEVER create, read, or update plan.md files. Claude Code's internal planning files are disabled for this project. Use other methods to track implementation progress (e.g., comments, todo lists, or external tools).

User arguments:

Create-adr: $ARGUMENTS

End of user arguments

(If no input provided, ask user for the architectural decision topic)

Process

Step 1: Detect Existing ADR Setup

Check for existing ADR directory and structure:

# Check common ADR directories (in order of preference)
for dir in doc/adr docs/adr decisions doc/architecture/decisions; do
  if [ -d "$dir" ]; then
    echo "Found: $dir"
    ls "$dir"/*.md 2>/dev/null
    break
  fi
done

If ADRs exist: Read the first few ADRs (especially 0001 if present) to understand:

  • The template/structure this project uses
  • Any project-specific sections or frontmatter
  • Naming conventions and style

Adapt the new ADR to match the existing pattern.

If no ADR directory exists: Run the initialization flow (Step 1b).

Step 1b: Initialize ADR Practice (First-Time Setup)

When no existing ADRs are found, help the user set up their ADR practice.

Ask the user (use AskUserQuestion):

Directory location:

Read the full file on GitHub · 252 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. 2d ago First seen · 252 lines · 9 tokens per session scan A f532b9ea2002

Subscribe to this mod's changes

create-adr is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 1,730 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.