Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hamr0/agentic-toolkitnpx agentmods add commands/hamr0/agentic-toolkit/live-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/commands/hamr0/agentic-toolkit/live-canvas)<a href="https://agentmods.dev/commands/hamr0/agentic-toolkit/live-canvas"><img src="https://agentmods.dev/badge/commands/hamr0/agentic-toolkit/live-canvas.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 5.1 | $0.00046 | $0.09979 |
| Opus 5 | $0.00023 | $0.04990 |
| Sonnet 5 | $0.00009 | $0.01996 |
| Haiku 4.5 | $0.00005 | $0.00998 |
Grade A, and why
live-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 yesterday.
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
100% identical to live-canvas — 0 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 — 1,086 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live Canvas Skill
This skill implements a complete design exploration workflow: interview, generate variations, collect feedback, refine, preview, and finalize.
CRITICAL: Cleanup Behavior
All temporary files MUST be deleted when the process ends, whether by:
- User confirms final design → cleanup, then generate plan
- User aborts/cancels → cleanup immediately, no plan generated
Never leave .claude-design/ or __live_canvas routes behind. If the user says "cancel", "abort", "stop", or "nevermind" at any point, confirm and then delete all temporary artifacts.
Feedback Modes — always ask the user
Live Canvas supports two feedback transports. The user picks every time — never auto-select.
- Live channel (Claude Code only): the overlay POSTs each Save to a local MCP channel server; feedback arrives in the active session as a
<channel source="live-canvas" ...>tag. Requires the session was launched withlive-claude(orclaude --dangerously-load-development-channels plugin:live-canvas-channel@live-canvas-marketplace) — channels are still an experimental Claude Code feature and a plainclaudesession silently drops the notifications. Any qualifying session can claim the channel by callingmcp__live-canvas__channel_open; only one holds it at a time. - JSON file (universal): each Save accumulates locally; Submit writes
.claude-design/feedback.jsonl(or downloads the JSON). User says "check" or pastes the file when ready. Works in any host.
Host detection — do this first
This SKILL.md is the Claude Code variant of the skill. Same content is mirrored as docs for Droid/Amp/Opencode under packages/<tool>/ beside the other capabilities, but those tools don't support the MCP channel.
If running under Droid, Amp, or Opencode (not Claude Code):
- Skip the mode question entirely.
- Announce:
📝 JSON mode (Live channel requires Claude Code). - Proceed to Phase 1 with
channelUrlomitted in the overlay init. - Never mention the channel plugin.
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.
- yesterday Changed · +2 lines · -4 tokens per session c2c02b0ed754
- 7d ago First seen · 1,084 lines · 50 tokens per session scan A 94eb6866fb35
live-canvas is a command published in the GitHub repository hamr0/agentic-toolkit (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 9,979 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to live-canvas, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
live-canvas
Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.
meta-prompt
Turn a rough request or the preceding conversation into a grounded, ready-to-run prompt for another agent. Use when the user asks to write a prompt, meta-prompt, or briefing for a separate agent session — "write a prompt for another instance", "brief another agent", "prepare a prompt I can copy-paste", "write this up…
analyze-git
Perform a comprehensive analysis of the git repository to identify branches and worktrees that can be cleaned up. This is a READ-ONLY analysis - no deletions will be performed.
build-from-conversation
You are the master orchestrator for building a working, tested app from nothing but a conversation. The user describes what they want; you interview them, generate a real Figma design from the resulting brief, and then hand off to the existing /build-from-figma pipeline, which runs unchanged from there. "Talk to…
test-layer
Test architectural layer with coverage-first analysis.
submit-to-directories
Submit the product to the directory catalog in /.darkflow/directories.csv through a real browser, and track what has already been submitted.