adr

adr is a command for Claude Code from thapaliyabikendra/ai-artifacts. It costs 10 tokens per session (1,196 once invoked), scanned A, original, Apache-2.0.

A command that writes an Architecture Decision Record, or ADR, for an important technical choice. An ADR records the problem, options, constraints, decision, and trade-offs so the reasoning remains available later.

In plain words
What is it for?
Use it to document why a system uses a particular architecture, tool, integration, or implementation approach.
Why use it?
It prevents important design decisions from being lost in chat, tickets, or personal memory.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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/thapaliyabikendra/ai-artifacts/adr
Clone the repo
git clone --depth 1 https://github.com/thapaliyabikendra/ai-artifacts

Made for: Claude Code.

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/thapaliyabikendra/ai-artifacts/adr.svg)](https://agentmods.dev/commands/thapaliyabikendra/ai-artifacts/adr)
Your own site
<a href="https://agentmods.dev/commands/thapaliyabikendra/ai-artifacts/adr"><img src="https://agentmods.dev/badge/commands/thapaliyabikendra/ai-artifacts/adr.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,196 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 $0.00010 $0.01196
Opus 5 $0.00005 $0.00598
Sonnet 5 $0.00002 $0.00239
Haiku 4.5 $0.00001 $0.00120

Measured 6d ago against content hash db5b62cfd542, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/arch/adr.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Architecture Decision Record

Title: $ARGUMENTS.title Number: $ARGUMENTS.number

Instructions

Step 1: Determine ADR Number

If number not provided:

  1. Search docs/architecture/decisions/ for existing ADRs
  2. Find highest number: ADR-NNNN-*.md
  3. Increment by 1

Step 2: Gather Context

Before writing, consider:

  1. What problem are we solving?
  2. What options were considered?
  3. What constraints exist?
  4. Who are the stakeholders?
  5. What are the trade-offs?

Step 3: Generate ADR

# ADR-[NNNN]: [Title]

**Date**: [YYYY-MM-DD]
**Status**: Proposed | Accepted | Deprecated | Superseded by ADR-XXXX
**Deciders**: [List of people involved]
**Technical Story**: [Link to issue/story if applicable]

## Context

[Describe the context and problem statement. What is the issue that we're seeing that is motivating this decision?]

### Current State

[Describe how things work today, if applicable]

### Problem Statement

[Clear statement of the problem to be solved]

### Constraints

- [Constraint 1: e.g., Must work with existing database]
- [Constraint 2: e.g., Budget limitation]
- [Constraint 3: e.g., Timeline pressure]

## Decision Drivers

- [Driver 1: e.g., Performance requirements]
- [Driver 2: e.g., Maintainability]
- [Driver 3: e.g., Team expertise]
- [Driver 4: e.g., Cost]

## Considered Options

### Option 1: [Name]

[Brief description]

**Pros:**
- [Pro 1]
- [Pro 2]

**Cons:**
- [Con 1]
- [Con 2]

**Effort**: Low | Medium | High
**Risk**: Low | Medium | High

### Option 2: [Name]

[Brief description]

**Pros:**
- [Pro 1]
- [Pro 2]

**Cons:**
- [Con 1]
- [Con 2]

**Effort**: Low | Medium | High
**Risk**: Low | Medium | High

### Option 3: [Name]

[Brief description]

**Pros:**
- [Pro 1]
- [Pro 2]

**Cons:**
- [Con 1]
- [Con 2]

**Effort**: Low | Medium | High
**Risk**: Low | Medium | High

## Decision

**Chosen Option**: [Option N] - [Name]

[Justify why this option was selected over others]

### Rationale

[Detailed explanation of why this decision was made, referencing the decision drivers]

## Consequences

### Positive

- [Positive consequence 1]
- [Positive consequence 2]

### Negative

- [Negative consequence 1 and how we'll mitigate it]
- [Negative consequence 2 and how we'll mitigate it]

### Neutral

- [Neutral observation]

## Implementation

### Action Items

- [ ] [Action 1]
- [ ] [Action 2]
- [ ] [Action 3]

### Timeline

| Phase | Task | Target Date |
|-------|------|-------------|
| 1 | [Task] | [Date] |
| 2 | [Task] | [Date] |

### Success Metrics

| Metric | Current | Target |
|--------|---------|--------|
| [Metric 1] | [Value] | [Value] |
| [Metric 2] | [Value] | [Value] |

## Related Decisions

- [ADR-XXXX](./ADR-XXXX-title.md): [Relationship]
- [ADR-YYYY](./ADR-YYYY-title.md): [Relationship]

## References

- [Link to relevant documentation]
- [Link to research/analysis]
- [Link to similar decisions elsewhere]

---

## Review History

| Date | Reviewer | Decision |
|------|----------|----------|
| [Date] | [Name] | Proposed |
| [Date] | [Name] | Accepted |

Read the full file on GitHub · 224 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. 6d ago First seen · 224 lines · 10 tokens per session scan A db5b62cfd542

Subscribe to this mod's changes

adr is a command published in the GitHub repository thapaliyabikendra/ai-artifacts (24 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 1,196 once invoked, about $0.0001 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.