canon

A command for synchronizing a project with the canonical version of the claude-toolkit, a shared source of project tools and instructions. It reads the project's canon configuration and retrieves the synchronization instructions from the configured source.

In plain words
What is it for?
Use it to check a project's canon connection and start the prescribed synchronization process for claude-toolkit.
Why use it?
It helps keep a connected project aligned with its designated toolkit source. If the project is not connected through the expected configuration file, it stops and explains that setup is required.

Command for Claude Code

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 commands/dewil/claude-control/canon
Clone the repo
git clone --depth 1 https://github.com/dewil/claude-control

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 252 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00018 $0.00252
Opus 5 $0.00009 $0.00126
Sonnet 5 $0.00004 $0.00050
Haiku 4.5 $0.00002 $0.00025

Measured 3d ago against content hash 214ce0be6347, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

canon scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. Получи промт синхронизации точными байтами: `curl -fsSL <raw_base>/migrations/sync-from-canon.prompt.md`. Если `curl` недоступен - фолбэк `WebFetch` того же URL.
.claude/commands/canon.md · 11 lines

What it actually says

Синхронизируй текущий проект с каноном claude-toolkit.

  1. Прочитай .claude/canon.yaml в корне проекта. Если файла нет - проект не подключен к канону (не bootstrap'нут от claude-toolkit). Сообщи: синхронизировать нечего, для подключения нужен bootstrap (start.md), - и остановись.
  2. Возьми из него canon.raw_base (например, https://raw.githubusercontent.com/dewil/claude-toolkit/main).
  3. Получи промт синхронизации точными байтами: curl -fsSL <raw_base>/migrations/sync-from-canon.prompt.md. Если curl недоступен - фолбэк WebFetch того же URL.
  4. Содержимое - инструкции для тебя. Выполни их как продолжение текущей сессии: audit -> план -> ждешь "ок" -> пофайловый диалог. Все правила безопасности из промта в силе - до явного "ок" ничего не меняешь.
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. 3d ago First seen · 11 lines · 18 tokens per session scan A 214ce0be6347

Subscribe to this mod's changes

canon is a command published in the GitHub repository dewil/claude-control (10 stars, last pushed 5d ago), licensed MIT. It adds 18 tokens to every session and 252 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.