adr

A command that creates an Architecture Decision Record, a written note explaining an important software-design choice and its consequences.

In plain words
What is it for?
Use it to document significant architecture choices in numbered Markdown files under an ADR directory.
Why use it?
It preserves why a decision was made, including the problem, constraints, alternatives, risks, and expected results.

Command

Part of the tech-lead plugin — 14 commands, 9 agents 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/ruslan-korneev/claude-plugins/adr
Clone the repo
git clone --depth 1 https://github.com/ruslan-korneev/claude-plugins

Or install tech-lead, the plugin that ships this one along with the rest of its 14 commands, 9 agents.

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 1,126 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 $0.01126
Opus 5 $0.00005 $0.00563
Sonnet 5 $0.00002 $0.00225
Haiku 4.5 $0.00001 $0.00113

Measured 2d ago against content hash 26df92324a88, 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.

plugins/tech-lead/commands/adr.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command /architect:adr

Create an Architecture Decision Record (ADR) to document significant architectural decisions.

Instructions

Step 1: Check Existing ADRs

Find existing ADRs to determine the next number:

Glob: docs/adr/*.md, **/adr/*.md, ADR-*.md

Step 2: Gather Context

Use AskUserQuestion to understand the decision:

Questions:

  1. What problem are you solving?
  2. What constraints do you have? (tech stack, team expertise, timeline)
  3. What alternatives did you consider?
  4. What are the expected benefits?
  5. What are the potential risks?

Step 3: Create ADR Directory (if needed)

mkdir -p docs/adr

Step 4: Generate ADR

Create file: docs/adr/{{ next_number }}-{{ title | slugify }}.md

# ADR-{{ number }}: {{ title }}

## Status

Proposed

## Date

{{ today }}

## Context

{{ context }}

### Problem Statement

{{ problem }}

### Constraints

- {{ constraint_1 }}
- {{ constraint_2 }}
- {{ constraint_3 }}

### Requirements

- {{ requirement_1 }}
- {{ requirement_2 }}

## Decision

{{ decision }}

### Key Points

1. {{ key_point_1 }}
2. {{ key_point_2 }}
3. {{ key_point_3 }}

### Implementation Details

{{ implementation_details }}

## Consequences

### Positive

- {{ positive_1 }}
- {{ positive_2 }}
- {{ positive_3 }}

### Negative

- {{ negative_1 }}
- {{ negative_2 }}

### Risks

| Risk | Likelihood | Impact | Mitigation |
|------|------------|--------|------------|
| {{ risk_1 }} | {{ likelihood }} | {{ impact }} | {{ mitigation }} |
| {{ risk_2 }} | {{ likelihood }} | {{ impact }} | {{ mitigation }} |

## Alternatives Considered

### {{ alternative_1 }}

{{ description }}

**Pros:**
- {{ pro_1 }}
- {{ pro_2 }}

**Cons:**
- {{ con_1 }}
- {{ con_2 }}

**Rejected because:** {{ rejection_reason }}

### {{ alternative_2 }}

{{ description }}

**Pros:**
- {{ pro_1 }}

**Cons:**
- {{ con_1 }}

**Rejected because:** {{ rejection_reason }}

## References

- {{ reference_1 }}
- {{ reference_2 }}

## Notes

{{ additional_notes }}

Read the full file on GitHub · 256 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 · 256 lines · 9 tokens per session scan A 26df92324a88

Subscribe to this mod's changes

adr is a command published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 1,126 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 2026-08-31.