A short Architecture Decision Record, or ADR, that documents one important repository decision and why it was made.

Use it to create and index a decision under docs/adr, replace an outdated decision, and validate the resulting document.

It gives future maintainers a concise record of changes that affect project structure, publishing, validation, licensing, layout, or policy.

adr-writer — Skill for Claude Code and Codex by stark-ai-de

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 stark-ai-de/agent-skills --skill adr-writer

Clone the repo

git clone --depth 1 https://github.com/stark-ai-de/agent-skills

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/stark-ai-de/agent-skills/adr-writer/github.svg)](https://agentmods.dev/skills/stark-ai-de/agent-skills/adr-writer)

Your own site

<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/adr-writer"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/adr-writer/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/stark-ai-de/agent-skills/adr-writer"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/adr-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 609 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	$0.00051	$0.00609
Opus 5	$0.00026	$0.00304
Sonnet 5	$0.00010	$0.00122
Haiku 4.5	$0.00005	$0.00061

Measured 11d ago against content hash 26f20cbddc1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

adr-writer 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 11d 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.

incubator/skills/repo-maintenance/adr-writer/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADR Writer

Goal

Create a short Architecture Decision Record that captures one repo-level decision without turning it into long-form documentation.

When to use

A decision changes repo structure, publishing, validation, license, layout, or skill standards.
A previous ADR is superseded, deprecated, or rejected.
The user asks to document a repo-level decision.

When not to use

Tiny copy edits, typo fixes, or minor template polish.
Routine skill additions that follow existing standards.
Temporary implementation details that do not affect future maintainers.

Inputs to inspect

docs/adr/README.md
docs/adr/TEMPLATE.md
Existing docs/adr/NNNN-*.md files
The decision context, current repo docs, and validation requirements

Workflow

Identify the single decision sentence.
Check docs/adr/README.md and the latest ADR number.
Create the next docs/adr/NNNN-short-title.md.
Use docs/adr/TEMPLATE.md or incubator/skills/repo-maintenance/adr-writer/assets/adr-template.md.
Keep the ADR under 250 words, with a target of 120 to 180 words.
Update the ADR index in docs/adr/README.md.
Run ADR validation.

Safety rules

Do not write long ADRs.
Do not rewrite accepted ADRs; create a superseding ADR instead.
Do not document secrets, private internal details, customer data, or credentials.
Do not invent decision history. Mark uncertain decisions as Proposed.

References

Read only when needed:

assets/adr-template.md for the compact ADR template.

Scripts

Use only when the user wants a new ADR file created:

npm run adr:new -- "Use category-based skill folders"

Output format

Return:

ADR path
Decision sentence
Word count
Validation result
Recommended next action

Completion criteria

The ADR records exactly one repo-level decision.
The ADR is under 250 words.
The ADR index is updated.
ADR validation passes.

Failure modes

If the decision is unclear, ask for the decision sentence before writing.
If the next ADR number cannot be determined, stop and report the conflicting files.
If validation fails, report the failing ADR rule and the file path.

Read the full file on GitHub · 90 lines

Files

What ships with it

1 file 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.

assets/adr-template.md 489 B

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.

11d ago First seen · 90 lines · 51 tokens per session scan A 26f20cbddc1e

Subscribe to this mod's changes

adr-writer is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 609 once invoked, about $0.0003 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.

Writing and docs adr agent-skills ai-agents codex developer-tools openai-codex

adr-writer