A tool for creating Architecture Decision Records, or documents that explain important technical choices, alternatives, evidence, and trade-offs. It writes the documents to the repository’s docs/adr folder.

Use it to discover, generate, capture, or prepare decision documents from repository evidence and human input.

It preserves why an architectural decision was made so future developers do not repeat old debates or change important structure accidentally.

adrgen — Skill for Claude Code and Codex by stefanrossmeier

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.

Any agent

npx skills add stefanrossmeier/ai-craftkit --skill adrgen

Clone the repo

git clone --depth 1 https://github.com/stefanrossmeier/ai-craftkit

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/stefanrossmeier/ai-craftkit/adrgen/github.svg)](https://agentmods.dev/skills/stefanrossmeier/ai-craftkit/adrgen)

Your own site

<a href="https://agentmods.dev/skills/stefanrossmeier/ai-craftkit/adrgen"><img src="https://agentmods.dev/badge/skills/stefanrossmeier/ai-craftkit/adrgen/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/stefanrossmeier/ai-craftkit/adrgen"><img src="https://agentmods.dev/badge/skills/stefanrossmeier/ai-craftkit/adrgen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,221 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.02221
Opus 5.5	$0.00016	$0.00888
Sonnet 5.5	$0.00008	$0.00444
Haiku 4.5	$0.00004	$0.00222

Measured 1mo ago against content hash 7a2e1e10d117, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adrgen 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 1mo 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.

skills/adrgen/SKILL.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adrgen Skill

Command: /adrgen

adrgen supports architecture decision work while keeping a strict boundary between what the repository implements and what humans explicitly decided.

Modes

/adrgen discover
/adrgen generate
/adrgen capture
/adrgen prepare

Treat additional user text as plain-language scope or source material, not shell-style flags.

`discover`

Find architecture-significant choices that appear in the repository but are not adequately documented.

Default output:

docs/adr/ADR_CANDIDATES.md
docs/adr/README.md

Discovery identifies implemented decision candidates. It must not claim that a choice was historically accepted, or invent why it was chosen, merely because the code consistently implements it.

Good candidates usually have meaningful consequences for boundaries, data ownership, integration, deployment, security, reliability, technology/platform commitment, or future change cost.

Do not treat ordinary implementation details, style conventions, or every dependency as ADR-worthy.

`generate`

Turn reviewed/selected candidates into ADR drafts.

Read:

docs/adr/ADR_CANDIDATES.md
docs/adr/README.md
docs/adr/*.md

Generate only candidates explicitly marked selected/approved/ready, or directly requested by the user.

Default decision status for a candidate inferred from repository implementation is PROPOSED, even when the implementation already exists. Record implementation separately as IMPLEMENTED, PARTIAL, or UNKNOWN.

An ADR may be marked ACCEPTED only when explicit human evidence establishes acceptance, for example:

user-provided confirmation
existing decision documentation
meeting/discussion notes
issue or pull-request decision text
an authoritative project document that clearly records the decision

Code shape alone is not evidence of historical acceptance.

`capture`

Turn an explicit human decision source into an ADR.

Typical sources:

meeting notes or transcript
issue/PR discussion
architecture review notes
user-provided decision summary
existing design document

Read the full file on GitHub · 346 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · -1,695 lines · +40 tokens per session 7a2e1e10d117
2mo ago First seen · 2,041 lines · 0 tokens per session scan A 6524da44390e

Subscribe to this mod's changes

adrgen is a skill published in the GitHub repository stefanrossmeier/ai-craftkit (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,221 once invoked, about $0.0002 per session on Opus 5.5. 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.

Writing and docs adr ai-agents ai-assisted-development developer-tools documentation mermaid

adrgen next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
adrgenstefanrossmeier/ai-craftkit	Skill	5	4d ago	Apache-2.0	A	40	Claude Code, Codex
architecture-decision-record-maintainer-skillarchitecture-decision-record/architecture-decision-record	Skill	17k	8d ago	none	A	92	Claude Code, Codex
architecture-decision-record-skillarchitecture-decision-record/architecture-decision-record	Skill	17k	8d ago	none	A	108	Claude Code, Codex
atlas-adrtonone-ai/tonone	Skill	77	23d ago	MIT	A	51	Claude Code
bootstrapEvolveHQ/docflow	Skill	16	15d ago	MIT	A	114	Claude Code, Codex
agent-waveEvolveHQ/docflow	Skill	16	15d ago	MIT	A	82	Claude Code, Codex
new-planEvolveHQ/docflow	Skill	16	15d ago	MIT	A	118	Claude Code, Codex