agentmods.dev

katashiro-canvas-writing

katashiro-canvas-writing is a skill for Claude Code, Codex from brettchien/katashiro. It costs 0 tokens per session (2,436 once invoked), scanned A, original, MIT.

A writing guide for making structured Markdown documents, such as reports, design documents, comparison pages, and technical proposals, on a Katashiro canvas.

In plain words
What is it for?
Use it to write reports, design documents, RFCs, references, and comparisons with cards, callouts, tables, diagrams, and other supported formatting.
Why use it?
It helps organize information for scanning instead of presenting a long wall of plain text.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

not rated 10repo 3d ago A scan 0 tokens original MIT

Good fit Use it to write reports, design documents, RFCs, references, and comparisons with cards, callouts, tables, diagrams, and other supported formatting.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brettchien/katashiro/katashiro-canvas-writing
View source ↗ brettchien/katashiro
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 brettchien/katashiro --skill katashiro-canvas-writing
Clone the repo
git clone --depth 1 https://github.com/brettchien/katashiro

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 katashiro-canvas-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/brettchien/katashiro/katashiro-canvas-writing/github.svg)](https://agentmods.dev/skills/brettchien/katashiro/katashiro-canvas-writing)
Your own site
<a href="https://agentmods.dev/skills/brettchien/katashiro/katashiro-canvas-writing"><img src="https://agentmods.dev/badge/skills/brettchien/katashiro/katashiro-canvas-writing/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 katashiro-canvas-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/brettchien/katashiro/katashiro-canvas-writing"><img src="https://agentmods.dev/badge/skills/brettchien/katashiro/katashiro-canvas-writing.svg" alt="Reviewed on agentmods" width="80" 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 2,436 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 $0.00000 $0.02436
Opus 5.5 $0.00000 $0.00974
Sonnet 5.5 $0.00000 $0.00487
Haiku 4.5 $0.00000 $0.00244

Measured 4d ago against content hash e5bedc843702, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

katashiro-canvas-writing 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 4d 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/katashiro-canvas-writing/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

katashiro-canvas-writing

A markdown canvas is a document the user reads beside the chat. Plain paragraphs and bullet lists work, but the canvas has blocks that make a document scannable. This skill says which block for which job, the few syntaxes that break, and how to edit without fighting the editor.

Requirements

  • The current chat is a Katashiro chat, so katashiro.canvas_* tools are available.
  • For a page the user should interact with (sort, filter, simulate), use an html canvas instead, and the katashiro-canvas-file skill to upload it. For an interactive system diagram, use katashiro-archify. This skill is about markdown (and slides) canvases.

1. Pick the block by what the content is

The content is… Write it as Not as
2–4 parallel things to compare (options, axes, principles) ::: cards with one ### per card three paragraphs in a row
A rule, a warning, a caveat the reader must not miss > [!NOTE] / [!TIP] / [!IMPORTANT] / [!WARNING] / [!CAUTION] (optional title after the marker) bold text in a paragraph
A short good/bad example line > ✅ … / > ⚠️ … / > ℹ️ … (emoji callout, no title row; only these three, and the emoji must be the first character — ❌ / 💡 stay a plain quote) a quote with no colour
Fields, options, numbers with several attributes a table (header row, ---: for numbers) nested bullets
Terms and their meanings, events and when they fire definition list: Term then : meaning on the next line **Term**: meaning paragraphs
An enum or a list of values a bullet list, one value per line a · b · c · d on one line
A source, a version, an aside a footnote [^1] with [^1]: … at the end parentheses in the sentence
The one phrase that carries the point ==highlight== (once or twice per document) bold everywhere
Something that is not what it seems ++underline++ sparingly ALL CAPS
Architecture, flow, sequence a ```mermaid fence (see §3) an ASCII drawing
Code, JSON, commands a fenced block with its language inline code for multi-line text

Read the full file on GitHub · 163 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. 4d ago First seen · 163 lines · 0 tokens per session scan A e5bedc843702

Subscribe to this mod's changes

katashiro-canvas-writing is a skill published in the GitHub repository brettchien/katashiro (10 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,436 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 2026-11-02.

DocumentsWriting and docsacpai-agentsbrowser-automationchrome-extensionmanifest-v3mcp
Related

katashiro-canvas-writing compared with skills from other repositories

katashiro-canvas-writing next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
katashiro-canvas-writingbrettchien/katashiroSkill103d agoMITA0Claude Code, Codex
browser-automationCrawlio-app/crawlio-browserSkill82mo agoApache-2.0A68Claude Code
web-researchCrawlio-app/crawlio-browserSkill82mo agoApache-2.0A26Claude Code
cloneCrawlio-app/crawlio-browserSkill82mo agoApache-2.0A21Claude Code
compareCrawlio-app/crawlio-browserSkill82mo agoApache-2.0A22Claude Code
dossierCrawlio-app/crawlio-browserSkill82mo agoApache-2.0A19Claude Code
extractCrawlio-app/crawlio-browserSkill82mo agoApache-2.0A27Claude Code