canon

canon is a skill for Claude Code from tomoking2004/claude-plugins. It costs 141 tokens per session (2,886 once invoked), scanned A, original, MIT.

規則体系(全 SKILL.md と正典)の全体を見直し,溜まった重複と食い違いを解消して,実行のたびに読まれる定義の量を減らす.「規則を見直して」「定義全体を整理して」「質が落ちた」など,一回の失敗でなく定義全体の手入れを求められたとき,または /heal:skill が見直しを勧めたときに使う.一回の失敗の修正は /heal:skill を使う..

Skill for Claude Code

Written for Claude Code: dynamic context !`command`.

Install with agentmods
npx agentmods add skills/tomoking2004/claude-plugins/canon
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 tomoking2004/claude-plugins --skill canon
Clone the repo
git clone --depth 1 https://github.com/tomoking2004/claude-plugins

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 canon

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomoking2004/claude-plugins/canon/github.svg)](https://agentmods.dev/skills/tomoking2004/claude-plugins/canon)
Your own site
<a href="https://agentmods.dev/skills/tomoking2004/claude-plugins/canon"><img src="https://agentmods.dev/badge/skills/tomoking2004/claude-plugins/canon/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 canon

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomoking2004/claude-plugins/canon"><img src="https://agentmods.dev/badge/skills/tomoking2004/claude-plugins/canon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,886 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 $0.00141 $0.02886
Opus 5.5 $0.00056 $0.01154
Sonnet 5.5 $0.00028 $0.00577
Haiku 4.5 $0.00014 $0.00289

Measured today against content hash 59422dc9b524, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

canon 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 today.

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.

plugins/heal/skills/canon/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

対象:規則体系——全 SKILL.md と,それらが従う正典(BEAUTY.md・RUBRIC.md 等).

前回の見直しからの状態

!git rev-parse --git-dir >/dev/null 2>&1 || { echo "(git リポジトリではない)"; exit 0; }; q(){ git -c core.quotepath=off ls-tree --full-tree -r -l "$r" | grep -E '(SKILL|BEAUTY|RUBRIC)\.md$' | { s=0; while read -r a b c z p; do s=$((s+z)); done; echo "$s"; }; }; h=$(git log --format='%h %s' 2>/dev/null | grep -m1 ' chore: review the canon$' | cut -d' ' -f1); [ -n "$h" ] || { echo "(見直しの記録なし)"; exit 0; }; r=$h; x=$(q); r=HEAD; y=$(q); echo "前回の見直し:$(git log -1 --format='%h %ad' --date=short "$h")"; echo "以降の定義の変更:$(git log --oneline "$h..HEAD" -- ':/*SKILL.md' ':/*BEAUTY.md' ':/*RUBRIC.md' | wc -l) 件"; echo "定義の量:$x → $y バイト"

前回の見直しコミットの本文(持ち越しの在処)

!h=$(git log --format='%h %s' 2>/dev/null | grep -m1 ' chore: review the canon$' | cut -d' ' -f1); b=$([ -n "$h" ] && git log -1 --format=%B "$h" 2>/dev/null); [ -n "$b" ] && echo "$b" || echo "(持ち越しなし——見直しの記録が無い)"

直近のコミットの全文(声・言語・書式の手本)

!b=$(git log -5 --format='──── %h%n%B' 2>/dev/null); [ -n "$b" ] && echo "$b" || echo "(手本なし——コミットがまだ無い)"

手順

  1. 合図を見る:git リポジトリでなければ,リポジトリのある環境で実行するよう伝えて終える.上の状態を下の「合図」に照らす.合図が無ければ前回の持ち越し(終えられずコミット本文に残した項目)を片づけることだけを行い,持ち越しも無ければ合図が無いことを1行で伝えて終える.
  2. 旧版を残す:作業ツリーを清潔にしてから始める——直前のコミットが定義の旧版になる.
  3. 変更を集める:前回の見直し以降の定義の変更を git log で列挙し,それらに手を付ける前に持ち越しを片づける.見直しの記録が無ければ全履歴を対象にする.1回に扱う範囲は精度を保てる量に限り,残りは持ち越す.
  4. 節ごとに決める:〈残す/畳む/移す/消す〉を下の「基準」で決める.重複は字面でなく文意で探す.長い節を重複と推測せず,類似の組を数えてから決める——0に近ければ削らず,読む範囲を分ける.
  5. 対照する:旧版の規則と確かめ方を数え,その一つひとつが新版のどこにあるかを指す.意図して外したものは理由つきで列挙する.
  6. 分離して走査する:書き手の文脈を持たない検査役1人に観点(整合・実行(定義どおりに手順を進められるか)・言語)を通させる——意図を渡さず,何をいくつ数えたかを報告させる.全文の読みは美の基準が変わった後と公開・提出の前にそれぞれ1回だけとし,経緯を知らない新しい役に任せる.他の周回(走査と直しの一巡)では,1人が走査を変わった文とその参照先に当てる.目的を定める文書は意図に数えず渡す.検査役の担当から,機械の走査がゼロを返した項目を除く.検査役が製品・ツールの公式文書と照合するのは,それを語る文が変わったときと全文の読みだけとする.検査役のゼロは,確定を差し止める指摘(止める指摘)のゼロを指す——事実の誤り・目的に答えていない・数えられる規則の違反・意味が取れないか二通りに読める・明晰さの欠け(一文に二つの事柄・息が続かない・同じ語の近接・字数合わせで痩せた).この定義を指示へ写す.検査役の指摘には確度(読みの確かさ)を高・中・低で付けさせ,「低」は止めず,書き手が判定して報告へ回す.止める指摘以外は採れるものを採り,残りは報告する.周回は3まで;止める指摘が残れば部分の手直しを重ねず,指摘のある単位を丸ごと目的に戻って書き直し,それでも消えなければ上流(方針・割り当て)を疑って問う.報告には立てた役と渡した材料(立てられない環境ならその旨)を書く.
  7. 片づける:作業の一時ファイル,同じ内容を写した余分な複製,前回の持ち越しで「消す」と明記したもの,空のフォルダを列挙し,承認を得てから消す.成果物か一時ファイルかを判定できないものは残す.
  8. 記録する:コミットメッセージの全文を提案して承認を得てから,件名 chore: review the canon でコミットする——この件名が次回の起点になるので変えない.本文には対照の要旨と持ち越しを上の手本の声(文の調子)で書き,72字以内で折り返す.トレーラは付けず,ツールが注入しても除く.

Read the full file on GitHub · 70 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. today First seen · 70 lines · 141 tokens per session scan A 59422dc9b524

Subscribe to this mod's changes

canon is a skill published in the GitHub repository tomoking2004/claude-plugins (3 stars, last pushed today), licensed MIT. It adds 141 tokens to every session and 2,886 once invoked, about $0.0006 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 2026-11-06.

Related

canon compared with skills from other repositories

canon next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
canontomoking2004/claude-pluginsSkill3todayMITA141Claude Code
skill-teilensebaskauf/skaile-community-librarySkill82mo agoMITA97Claude Code
show-and-sharesebaskauf/skaile-community-librarySkill82mo agoMITA74Claude Code
readme-prosebaskauf/skaile-community-librarySkill82mo agoMITA37Claude Code
skill-guideAndyElessar/skillsSkill211d agononeA102Claude Code
csharp-source-generatorAndyElessar/skillsSkill211d agononeA112Claude Code
plugin-creatorAndyElessar/skillsSkill211d agononeA181Claude Code