An interactive one-time setup wizard for Canonify, a system that stores canonical project-pattern documents called canons. It creates a CANONIFY.md routing file, a docs/ structure, and can optionally draft canons by scanning the codebase.

Use it to onboard Canonify in a fresh Git repository, choose documentation categories, create the initial structure, and seed project-pattern documents from existing code.

It removes the manual work of deciding how project knowledge should be organised before using Canonify. It also checks whether the repository is ready and detects common programming-language setups.

kickoff — Skill for Claude Code and Codex by ewebdzine: An interactive one-time setup wizard for Canonify, a system…

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/kickoff

Any agent

npx skills add ewebdzine/canonify --skill kickoff

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/kickoff.svg)](https://agentmods.dev/skills/ewebdzine/canonify/kickoff)

Your own site

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

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,117 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	$0.00096	$0.01117
Opus 5	$0.00048	$0.00558
Sonnet 5	$0.00019	$0.00223
Haiku 4.5	$0.00010	$0.00112

Measured 3d ago against content hash 353f01600c1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kickoff 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 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.

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/kickoff/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kickoff - set Canonify up in a repo

The onboarding gate. Run it ONCE in a fresh repo to stand up Canonify: a routing manifest (CANONIFY.md), a docs/ corpus of canons, and - if you want - an initial set of canons drafted from the codebase. It is an interactive wizard, not a silent file-creator.

Vocabulary: a canon is one canonical-pattern doc; CANONIFY.md is the manifest the gates (/canonify:plan / :build / :commit) route through. This gate creates both. The templates ship with the plugin at ${CLAUDE_PLUGIN_ROOT}/templates/.

How to run

Detect.
- Confirm this is a git repo (Canonify's staleness checks rely on git).
- Already set up? If CANONIFY.md exists at the repo root, do NOT re-run the survey - report what is there and offer to reconfigure (add categories, seed more canons) instead.
- Detect the stack to pre-fill sensible category names: *.csproj/*.sln -> .NET; pyproject.toml/ requirements.txt -> Python; package.json -> Node; go.mod -> Go; and so on. Categories are the docs/<area>/ folders (e.g. integrations, services, ui) - the project's own, not a fixed set.
Survey (ask a few; auto-detect the rest - keep it short):
- Auto-seed by scanning?
  - Scan and propose (recommended): discover the surface (third-party integrations, internal services, key subsystems, UI patterns) and propose a list of canons to confirm before writing any.
  - Start empty: just the skeleton; author canons later with /canonify:create-canon.
- Scheduled doctor backstop? Yes (weekly) / no, run it manually / later. A periodic /canonify:doctor sweep catches drift that accumulates between commits.
- Confirm the stack + category folders you detected.
Act.
- Write CANONIFY.md at the repo root from ${CLAUDE_PLUGIN_ROOT}/templates/CANONIFY.md.template, filling in the detected categories.
- Create the docs/<category>/ skeleton with a short INDEX.md per category.
- Optionally copy ${CLAUDE_PLUGIN_ROOT}/templates/doc-style.md into the repo (e.g. docs/doc-style.md) so authors have the house-style locally.
- If scanning: discover -> propose the canon list -> on confirm, run /canonify:create-canon in bulk over each target (index the code, draft in the house-style, register in CANONIFY.md + the category INDEX, stamp verified). Show progress; never silently generate a large batch.
- If scheduled doctor: set up a periodic /canonify:doctor run via the host's scheduling (a scheduled agent, or a repo cron) at the chosen cadence.

Read the full file on GitHub · 78 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.

3d ago First seen · 78 lines · 96 tokens per session scan A 353f01600c1a

Subscribe to this mod's changes

kickoff is a skill published in the GitHub repository ewebdzine/canonify (23 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 1,117 once invoked, about $0.0005 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 2026-08-30.

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