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 skills add Kevin-Liu-01/Agent-Machines --skill canvasgit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/canvas)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/canvas"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/canvas/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.
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/canvas"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/canvas.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00165 | $0.02370 |
| Opus 5 | $0.00082 | $0.01185 |
| Sonnet 5 | $0.00033 | $0.00474 |
| Haiku 4.5 | $0.00016 | $0.00237 |
Grade A, and why
canvas 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 11d 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.
This is a copy
83% identical to openbitfun-canvas — 91 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A canvas is a single .canvas.tsx file the IDE compiles so the user can open it beside the chat. Follow the workflow below in order.
Workflow
1. Decide whether to use a canvas
The trigger is user intent, not response shape. Ask: would the user benefit from viewing this output as its own standalone artifact, separate from the chat? If the output is a means to an end (a drafted message, a code fix, a dashboard in another tool), skip the canvas.
Use a canvas when the agent produces new standalone analytical output:
- Quantitative analyses and metrics breakdowns (e.g. "send 500 requests and tell me how many fail")
- Billing or account investigations that surface structured findings from database queries
- Security audits or architecture reviews with categorized findings
- Cross-system data analyses and overlap reports
- Structured data from MCP tools (Databricks, Datadog, etc.) where the data IS the deliverable
- Financial analyses, margin decompositions, usage trend reports
- Tables with more than a handful of rows that the user asked to see
Do NOT use a canvas when:
- The user asks for work in a specific tool — "create a Datadog dashboard" means give them a Datadog dashboard, not a canvas
- The user has a specific deliverable — "draft a support response", "fix this code", "make this PR"
- The user is working within an existing artifact — improving an HTML dashboard, editing an existing file
- The user is doing targeted debugging or active development, even if structured findings emerge along the way
- Short factual answers, one-off file edits, or quick clarifying questions
- MCP tools are queried as an intermediate step for a different deliverable (e.g. querying Stripe to draft a support reply)
2. Write the canvas
Location. Canvases live at /Users/<user>/.cursor/projects/<workspace>/canvases/<name>.canvas.tsx. The IDE only detects canvases written directly inside that exact directory — subfolders, alternate extensions, and other locations are not picked up. For a new canvas, always use the write file tool to create the .canvas.tsx file at that exact path; do not stop after telling the user the path or showing code in chat. Treat that managed canvases/ directory as pre-provisioned by Cursor itself: write the canvas file directly there and do not spend turns creating the directory with mkdir or checking whether it exists before writing. Listing its contents for other purposes (e.g. checking for existing canvases) is fine. If you can't determine the workspace directory from absolute paths already in your environment (terminals, transcripts, recently-viewed files), list ~/.cursor/projects/ rather than guessing. Use a descriptive kebab-case filename ending in .canvas.tsx; preserve acronym capitalization and lowercase the rest.
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.
- 11d ago First seen · 154 lines · 165 tokens per session scan A 1c84423cb658
canvas is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed yesterday), licensed MIT. It adds 165 tokens to every session and 2,370 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to openbitfun-canvas, differing in 91 lines, and is treated as a copy.
Other skills, from other repositories
21st-ui
Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.
harness-design-fuzzing
Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…
workspace-builder
Build ServiceNow App Engine Studio applications — sysscope creation, scoped tables, sysawworkspace with lists/forms, the sysux record chain behind UI Builder workspaces, data brokers, and application export readiness checks. Never create a UI Builder page by inserting a sysuxpage row.
ui-builder-patterns
Build ServiceNow UI Builder / Next Experience pages — macroponents, GraphQL/script data brokers, client state parameters, event handlers (NOWRECORDLIST etc.), and now-record-list/form component configuration.
widget-coherence
Build Service Portal widgets (spwidget) with synchronized server/client/HTML — data. initialization, ng-click + controller method matching, c.server.get action handlers, and Angular directive usage.
remotion
Create editable AI video projects with Remotion and React, then preview and render them to MP4. Use for vertical short videos, product demos, story-driven animations, HUD/tech visuals, feed ads, tutorial videos, subtitles, voiceover, sound effects, and code-based video iteration.