adr

adr is a command for coding agents from SyloRei/claude-godmode. It costs 33 tokens per session (818 once invoked), scanned A, original, MIT.

A command that writes an Architecture Decision Record, a short document explaining an important technical choice and its consequences. It produces sections for status, context, decision, and consequences.

In plain words
What is it for?
Use it to document one architectural decision based on a code change, its surrounding files, and related discussion.
Why use it?
It turns scattered change context into a consistent record that future developers can understand.

Command

Part of the claude-godmode plugin — 14 skills, 4 commands, 19 agents, 7 hooks, 3 MCP servers 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 commands/sylorei/claude-godmode/adr
Clone the repo
git clone --depth 1 https://github.com/SyloRei/claude-godmode

Or install claude-godmode, the plugin that ships this one along with the rest of its 14 skills, 4 commands, 19 agents, 7 hooks, 3 MCP servers.

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/commands/sylorei/claude-godmode/adr.svg)](https://agentmods.dev/commands/sylorei/claude-godmode/adr)
Your own site
<a href="https://agentmods.dev/commands/sylorei/claude-godmode/adr"><img src="https://agentmods.dev/badge/commands/sylorei/claude-godmode/adr.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 818 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 5.1 $0.00033 $0.00818
Opus 5 $0.00016 $0.00409
Sonnet 5 $0.00007 $0.00164
Haiku 4.5 $0.00003 $0.00082

Measured 5d ago against content hash df6f5e9cb420, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

commands/adr.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/adr — write an Architecture Decision Record

A focused, single-shot generator. Capture one architectural decision as a well-formed ADR. This is a reactive helper — it does not spawn agents and is not part of the spine.


The Job

  1. Identify the decision being recorded.
  2. Read the surrounding change/context.
  3. Produce a complete ADR with all four sections.

1. Gather context

Read whatever explains the decision — the relevant diff, the files it touches, and any motivating discussion in the request:

git diff --stat            # what changed
git log --oneline -10      # recent direction

Ask the user only what you cannot infer (e.g. alternatives considered, the driving constraint) — and when you ask, follow the shared recommendation convention (godmode:recommend-convention) in rules/godmode-recommend.md: its clarifying rendering leads with your best-inferred answer to override, not a blank prompt. So state what you'd record and invite correction:

I'll record the alternatives as in-process queue vs. Redis from the diff — tell me if I missed one.

(Not: "what alternatives did you consider?")

2. Produce the ADR

Emit a single Markdown document with these exact sections, in order:

# NNNN. <short title in imperative mood>

## Status

Proposed | Accepted | Superseded by ADR-MMMM   (pick one)

## Context

The forces at play: the problem, the constraints, the requirement that makes a
decision necessary. State facts, not the choice.

## Decision

The change being made, in active voice ("We will …"). One decision per record.

## Consequences

What becomes easier and what becomes harder as a result — both the positive and
the negative. Note follow-on work and any new constraints introduced.

3. Suggest a home

Suggest (do not require) a path like docs/adr/NNNN-title.md, numbering one above the highest existing ADR. Writing the file is a consequential step, so pause with the convention's confirm/proceed rendering — lead with a Recommended:

Read the full file on GitHub · 103 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. 5d ago First seen · 103 lines · 33 tokens per session scan A df6f5e9cb420

Subscribe to this mod's changes

adr is a command published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 818 once invoked, about $0.0002 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.