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 commands/opensesh/canvas-to-code/updategit clone --depth 1 https://github.com/opensesh/canvas-to-codeWrote 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/opensesh/canvas-to-code/update)<a href="https://agentmods.dev/commands/opensesh/canvas-to-code/update"><img src="https://agentmods.dev/badge/commands/opensesh/canvas-to-code/update.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 | $0.00024 | $0.01113 |
| Opus 5 | $0.00012 | $0.00557 |
| Sonnet 5 | $0.00005 | $0.00223 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
update 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/canvas-to-code:update — Bring this repo up to the latest plugin
Run this from any consumer repo (e.g. BOS-Mono/frontend) to update the installed Canvas-to-Code plugin to the latest on opensesh/canvas-to-code@main.
Why this exists
Claude Code's built-in /plugin update canvas-to-code keys off the version field in .claude-plugin/plugin.json. When a release ships docs/test/agent-prompt changes without a version bump (e.g. PRs #3/#4 both stayed at 0.4.0), /plugin update silently no-ops and the consumer keeps running stale agent prompts — confirmed gotcha, tracked in issue #2.
This command updates by git SHA, not version, so it always pulls the real main. The plugin's live files are the marketplace clone at ~/.claude/plugins/marketplaces/canvas-to-code-marketplace, so a fast-forward of that clone is the update.
Flags
| Flag | Behavior |
|---|---|
| (none) | Check, then update the cache to latest main if behind. Reports the commit delta. |
--check |
Dry run. Report local vs. remote version + SHA and how many commits behind. Changes nothing. |
--force |
Hard-refresh the cache even if SHAs already match (repairs a dirty/diverged cache). |
Procedure
Run these steps with Bash. Define the cache path once:
CACHE="$HOME/.claude/plugins/marketplaces/canvas-to-code-marketplace"
REPO="opensesh/canvas-to-code"
1. Preconditions
# Marketplace must be installed. If the cache is missing, stop and tell the user to run:
# /plugin marketplace add opensesh/canvas-to-code
# /plugin install canvas-to-code@canvas-to-code-marketplace
test -d "$CACHE/.git" || { echo "NOT_INSTALLED"; exit 0; }
gh auth status >/dev/null 2>&1 || echo "WARN: gh not authenticated — falling back to git ls-remote"
2. Read local + remote state
LOCAL_SHA=$(git -C "$CACHE" rev-parse HEAD)
LOCAL_VER=$(python3 -c "import json,sys;print(json.load(open('$CACHE/.claude-plugin/plugin.json'))['version'])")
git -C "$CACHE" fetch --quiet origin main
REMOTE_SHA=$(git -C "$CACHE" rev-parse origin/main)
REMOTE_VER=$(git -C "$CACHE" show origin/main:.claude-plugin/plugin.json | python3 -c "import json,sys;print(json.load(sys.stdin)['version'])")
BEHIND=$(git -C "$CACHE" rev-list --count "$LOCAL_SHA..$REMOTE_SHA")
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 · 96 lines · 24 tokens per session scan A 9a35bfbbdc6d
update is a command published in the GitHub repository opensesh/canvas-to-code (6 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 1,113 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 2026-08-31.
Other commands, from other repositories
workflow-automate
You are a workflow automation expert specializing in creating efficient CI/CD pipelines, GitHub Actions workflows, and automated development processes. Design and implement automation that reduces manual work, improves consistency, and accelerates delivery while maintaining quality and security.
ui-synth
Master orchestration command that synthesizes ALL LibreUIUX plugins - archetypal-alchemy, design-mastery, accessibility, security, performance, testing - into one cohesive, production-ready UI/UX implementation. The ultimate synthesis.
ui-modern
Generate a modern UI component with best practices and design system compliance.
performance-optimization
Optimize application performance end-to-end using specialized performance and optimization agents.
brand-identity
Guided workflow for creating comprehensive brand identity systems. Walks through discovery, strategy, visual identity, and guidelines creation.
design-audit
Systematic evaluation of existing designs against fundamental principles. Provides actionable feedback rooted in design theory and best practices.