scraps: Skill for Claude Code

.agents/skills/adr-check/SKILL.md

adr-check is a skill for Claude Code, Codex from boykush/scraps. It costs 72 tokens per session (582 once invoked), scanned A, original, MIT.

A change-checking skill that compares completed repository work with accepted architectural rules. Architectural rules are recorded decisions about how a codebase should be built and maintained.

In plain words
What is it for?
Use it after finishing code changes to read the applicable rules, inspect changed files, identify violations, and fix them without changing the rules in the working repository.
Why use it?
It helps catch rule violations before changes are pushed or after someone reports one. It limits the check to rules that apply to the repository and avoids treating unrelated guidance as a requirement.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is boykush/scraps's own configuration. It tells Claude Code and Codex how to work on scraps itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything scraps configures →

Reuse

Borrowing it

Nothing to install: this file belongs to boykush/scraps. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/boykush/scraps/main/.agents/skills/adr-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/boykush/scraps

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.

agentmods badge for adr-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/boykush/scraps/adr-check/github.svg)](https://agentmods.dev/skills/boykush/scraps/adr-check)
Your own site
<a href="https://agentmods.dev/skills/boykush/scraps/adr-check"><img src="https://agentmods.dev/badge/skills/boykush/scraps/adr-check/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.

agentmods 80×15 button for adr-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/boykush/scraps/adr-check"><img src="https://agentmods.dev/badge/skills/boykush/scraps/adr-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 582 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.00582
Opus 5.5 $0.00029 $0.00233
Sonnet 5.5 $0.00014 $0.00116
Haiku 4.5 $0.00007 $0.00058

Measured 23d ago against content hash 0a96dea6cda4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adr-check 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 23d 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.

.agents/skills/adr-check/SKILL.md · 25 lines

What it actually says

ルールとの照合

boykush/adr のルールは、各リポジトリの作業が守ること。ルールを実行する仕組みは無く、変更を読んでルールに照らす。

照合は作業を終えてから行う。作業の前や途中に読むと、作業が触れないルールまでセッションに載ってノイズになる。違反を指摘されて直すときは、指摘されたルールを読んで直す。

照合する

  1. list_rules でルールを読む。返るのは accepted の決定のルールだけ
  2. 文法は skill ade-rule-dsl の reference で確かめる。記憶や似た DSL から推し量らない
  3. ルールは、それを読んだセッションが作業しているリポジトリについての言明。パスはそのリポジトリの root から当てる
  4. 変更が、ルールの禁じるものを足していないか、触ったファイルに残していないか、ルールの求めるものを欠いていないかを見る
  5. ルールが当てはまるかを決めるのに理由が要るときだけ、get_decision で決定を読む。id が分からなければ list_decisions で探す。決定のうちルールに書かれていない部分は、作業を縛らない

違反があったら

  • 作業を直して、ルールを満たす
  • ルールを破らないと作業が成り立たないように見えたら、破らずにユーザーへ伝える。ルールを変えるのは boykush/adr で、作業しているリポジトリではない
  • ルールはリポジトリ自身の慣習として扱う。コードのコメントにも commit message にも PR にも、ルールの元になった決定を名指ししない
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. 23d ago First seen · 25 lines · 72 tokens per session scan A 0a96dea6cda4

Subscribe to this mod's changes

adr-check is a skill published in the GitHub repository boykush/scraps (45 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 582 once invoked, about $0.0003 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 2026-09-26.