Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add a8cteam51/claude-code-plugins/plugin install ai-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/a8cteam51/claude-code-plugins/publish)<a href="https://agentmods.dev/skills/a8cteam51/claude-code-plugins/publish"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/publish/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/a8cteam51/claude-code-plugins/publish"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/publish.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 | $0.00180 | $0.05148 |
| Opus 5.5 | $0.00072 | $0.02059 |
| Sonnet 5.5 | $0.00036 | $0.01030 |
| Haiku 4.5 | $0.00018 | $0.00515 |
Grade C, and why
publish scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
'<main class="wp-block-group" style="margin-top:0"><!-- wp:post-content {"align":"full","layout":{"type":"constrained"}} /--></main>', How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Put a page on the site
This moves a page built with ai-canvas:design onto the user's WordPress site, working in their own Chrome where they are already logged in. There is no password, key, or connection to set up. The page itself travels by clipboard, so it never passes through you as text; small scripts in the page do the rest. Run this only when the user asks for it.
bash "${CLAUDE_PLUGIN_ROOT}/scripts/canvas.sh" <command> DIR
What it needs
- Claude in Chrome (
mcp__claude-in-chrome__*). Loadtabs_context_mcp,tabs_create_mcp,navigate,computer,find,javascript_tool,browser_batch, andtabs_close_mcpin oneToolSearch. Without it, see "Without the browser tools". - The user logged in to wp-admin in that Chrome, as an Administrator.
- A block theme and Jamie's Visual HTML Editor active on the site. The plugin gives the block its full width and lets the owner click text and images to edit them.
"Check the site" below tests all three and says what is missing.
Rules for working in wp-admin
Each of these comes from a failure.
- Never type a password. If a login screen appears, ask the user to log in and wait.
- Take a screenshot before sending keys to a tab. Keys sent to a tab before its first screenshot go nowhere, with no error.
- Paste only into the Code editor. Never click, select, or type inside the visual canvas of a canvas page. The visual HTML editor starts editing whatever is touched, rewrites the whole block from the live document, and the editor saves that on its own a minute later.
- Script results are one short line of JSON: names, numbers, booleans, hashes. A result containing page markup,
key=valuetext, or an address with a?comes back as[BLOCKED: Cookie/query string data]. Build addresses yourself from the site address and the page number. - Leave the editor clean. Before leaving an editor tab it must be back in the visual view and not dirty. A dirty editor raises a "Leave site?" dialog that freezes the browser tools. If a step failed midway, run "Discard".
- Work in a tab you opened, and close it when you finish.
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 · 280 lines · 180 tokens per session scan C e8688726a537
publish is a skill published in the GitHub repository a8cteam51/claude-code-plugins (5 stars, last pushed 2d ago), licensed MIT. It adds 180 tokens to every session and 5,148 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts with the existing agent-browser CLI, including screenshots and keyboard or interaction checks. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser automation.