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.
npx agentmods add skills/dvdsgl/claude-canvas/documentnpx skills add dvdsgl/claude-canvas --skill documentgit clone --depth 1 https://github.com/dvdsgl/claude-canvasWrote 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.
[](https://agentmods.dev/skills/dvdsgl/claude-canvas/document)<a href="https://agentmods.dev/skills/dvdsgl/claude-canvas/document"><img src="https://agentmods.dev/badge/skills/dvdsgl/claude-canvas/document.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00028 | $0.00925 |
| Opus 5 | $0.00014 | $0.00463 |
| Sonnet 5 | $0.00006 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
document 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Canvas
Display markdown documents with optional text selection and diff highlighting.
Example Prompts
Try asking Claude:
- "Draft an email to the marketing team about the Q1 product launch"
- "Help me edit this blog post — show it so I can highlight the parts to revise"
- "Write a project proposal and let me review it"
- "Show me the README so I can select sections to update"
- "Compose a response to this customer complaint"
Scenarios
display (default)
Read-only document view with markdown rendering. User can scroll but cannot select text.
bun run src/cli.ts show document --scenario display --config '{
"content": "# Hello World\n\nThis is **markdown** content.",
"title": "My Document"
}'
edit
Interactive document view with text selection. User can click and drag to select text, which is sent via IPC in real-time.
- Renders markdown with syntax highlighting (headers, bold, italic, code, links, lists, blockquotes)
- Diff highlighting: green background for additions, red for deletions
- Click and drag to select text
- Selection automatically sent via IPC
bun run src/cli.ts spawn document --scenario edit --config '{
"content": "# My Blog Post\n\nThis is the **introduction** to my post.\n\n## Section One\n\n- Point one\n- Point two",
"title": "Blog Post Draft",
"diffs": [
{"startOffset": 50, "endOffset": 62, "type": "add"}
]
}'
email-preview
Specialized view for email content display.
bun run src/cli.ts show document --scenario email-preview --config '{
"content": "Dear Team,\n\nPlease review the attached document.\n\nBest regards,\nAlice",
"title": "RE: Project Update"
}'
Configuration
interface DocumentConfig {
content: string; // Markdown content
title?: string; // Document title (shown in header)
diffs?: DocumentDiff[]; // Optional diff markers for highlighting
readOnly?: boolean; // Disable selection (default: false for edit)
}
interface DocumentDiff {
startOffset: number; // Character offset in content
endOffset: number;
type: "add" | "delete";
}
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.
- 4d ago First seen · 133 lines · 28 tokens per session scan A 9c7b6187946d
document is a skill published in the GitHub repository dvdsgl/claude-canvas (1,510 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 925 once invoked, about $0.0001 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.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.