What is create-canon?

A guided tool for writing one canonical pattern document—a Markdown file describing how a part of a codebase works—and registering it in the repository index.

Use it to document a file, service, integration, or user-interface pattern with source-code references.

It turns code-based knowledge into findable documentation with evidence from the actual source.

create-canon — Skill for Claude Code and Codex by ewebdzine: A guided tool for writing one canonical pattern document

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 skills/ewebdzine/canonify/create-canon

Any agent

npx skills add ewebdzine/canonify --skill create-canon

Clone the repo

git clone --depth 1 https://github.com/ewebdzine/canonify

Made for: Claude Code, Codex.

Or install canonify, the plugin that ships this one along with the rest of its 8 skills.

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/ewebdzine/canonify/create-canon.svg)](https://agentmods.dev/skills/ewebdzine/canonify/create-canon)

Your own site

<a href="https://agentmods.dev/skills/ewebdzine/canonify/create-canon"><img src="https://agentmods.dev/badge/skills/ewebdzine/canonify/create-canon.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,527 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01527
Opus 5	$0.00000	$0.00763
Sonnet 5	$0.00000	$0.00305
Haiku 4.5	$0.00000	$0.00153

Measured 5d ago against content hash 67e0c089868f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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 5d 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/create-canon/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a canon

Canonify's authoring gate. A canon is one canonical-pattern doc (a .md); the root manifest CANONIFY.md indexes every canon by a one-line summary, and the lifecycle gates (plan / build / commit) route off those summaries. Where they consume the canon, this gate grows it: point it at a file, service, or design element and it writes a new canon and wires it into CANONIFY.md so the other gates can immediately route to it.

It codifies the workflow for authoring a canon: read the real code, cite file:line, draft from evidence, and ask only for what the code can't tell you.

How to run

Identify the target. The user points at one of:
- a file / class (a path or a type name),
- a service / integration (e.g. a third-party API client, a *Service wrapper),
- a design element (a UI pattern + its CSS/JS source). If nothing is named, ask once: "what file, service, or element should I turn into a canon?" Don't guess.
Place it. Decide the category + destination from CANONIFY.md's blocks and the existing docs/ folders - the repo defines its own categories. Don't impose a fixed taxonomy; read what categories already exist (the blocks in CANONIFY.md, the subfolders under docs/) and slot the canon into the matching one, creating a new category only when none fits. The destination is docs/<category>/<topic>.md. Infer the obvious case; confirm the destination path in one line.
Index the target (the evidence pass). Read the target in full and gather the proof every claim will cite:
- the wrapper / class and its public surface,
- how it's wired up / registered / constructed (DI, factory, entry point),
- config keys / settings and where they're read (file:line),
- real call sites (grep the repo),
- related types / canons it overlaps with. For a design element also read its source partial(s), any vendor library it depends on, and a reference template / view that uses it.

Read the full file on GitHub · 106 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.

5d ago First seen · 106 lines · 0 tokens per session scan A 67e0c089868f

Subscribe to this mod's changes

create-canon is a skill published in the GitHub repository ewebdzine/canonify (23 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,527 tokens. 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 2026-08-30.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens