adr

A guide for recording important software design decisions in an Architecture Decision Record, or ADR.

In plain words
What is it for?
Use it to create or update numbered decision files in a project's ADR folder while following the project's existing format.
Why use it?
It preserves why a decision was made, which alternatives were rejected, and what consequences it has, so future developers have the context.

Skill for Claude CodeCodex

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 skills/jackfranklin/dotfiles/adr
Any agent
npx skills add jackfranklin/dotfiles --skill adr
Clone the repo
git clone --depth 1 https://github.com/jackfranklin/dotfiles

Made for: Claude Code, Codex.

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 908 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 $0.00106 $0.00908
Opus 5 $0.00053 $0.00454
Sonnet 5 $0.00021 $0.00182
Haiku 4.5 $0.00011 $0.00091

Measured 2d ago against content hash 1dcb85b3fb09, 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/skills/adr/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR Skill

Captures a decision as an Architecture Decision Record in the project's ADR directory. ADRs record the why — context, the decision made, alternatives rejected, and consequences — not implementation details.

1. Resolve the project root and ADR directory

The project root is the working directory. Check for an existing ADR directory before creating one:

ls -d adrs/ docs/adr/ docs/decisions/ architecture/decisions/ 2>/dev/null | head -1

Use whichever exists. If none exist, default to adrs/ and create it:

mkdir -p adrs

2. Check for existing ADR format

If ADR files exist, read the most recent one to match its format and section naming exactly. Don't impose a different structure on a project that already has a convention.

3. Confirm the title and framing before drafting

Before writing a full ADR, confirm with the user in one sentence:

"I'll capture this as: '' — decision: . Does that framing look right?"

This avoids a full redraft if the angle is wrong.

4. Determine the next ADR number

ls adrs/[0-9]*.md 2>/dev/null | sort | tail -1

Parse the numeric prefix from the last file (e.g. 0003 from 0003-use-sqlite.md). Increment by one. If no files exist, start at 0001.

5. Derive the filename

Use the decision title in lowercase kebab-case:

adrs/<NNNN>-<kebab-title>.md

Example: adrs/0004-store-adrs-in-top-level-folder.md

6. Write the ADR

Use this template — keep each section concise (a few sentences to a short paragraph):

# <NNNN>. <Title>

Date: <YYYY-MM-DD>
Status: <Accepted | Proposed | Deprecated | Superseded by [NNNN](<link>)>

## Context

What situation, constraint, or requirement forced this decision? What was the problem space?

## Decision

What was chosen and why? State it directly.

## Alternatives Considered

What else was evaluated and why was it not chosen? This is the most important section for future readers — capture each rejected option and the specific reason it lost.

## Consequences

What gets easier? What gets harder? What is accepted as a trade-off?

Read the full file on GitHub · 109 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 · 109 lines · 106 tokens per session scan A 1dcb85b3fb09

Subscribe to this mod's changes

adr is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 9d ago), licensed MIT. It adds 106 tokens to every session and 908 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens