agentmods.dev

modellix-agent-canvas: Skill for Claude Code

.agents/skills/modellix-agent-canvas-open/SKILL.md

modellix-agent-canvas-open is a skill for Claude Code from Modellix/modellix-agent-canvas. It costs 54 tokens per session (378 once invoked), scanned A, original, MIT.

A tool for opening and inspecting Modellix Agent Canvas, a workspace for managing Modellix tasks inside coding-agent tools.

In plain words
What is it for?
Opening Canvas, checking its connection, configuring an API key in its credential field, and finding unfinished tasks to resume.
Why use it?
It checks that Canvas is connected to the current project and explains how to provide credentials or recover access when it cannot open normally.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

This is Modellix/modellix-agent-canvas's own configuration. It tells Claude Code how to work on modellix-agent-canvas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything modellix-agent-canvas configures →

Part of the modellix-agent-canvas plugin — 3 skills, 2 MCP servers shipped together

not rated 0repo 29d ago A scan 54 tokens original MIT
View source ↗ Modellix/modellix-agent-canvas
Reuse

Borrowing it

Nothing to install: this file belongs to Modellix/modellix-agent-canvas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Modellix/modellix-agent-canvas/main/.agents/skills/modellix-agent-canvas-open/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Modellix/modellix-agent-canvas

Made for: Claude Code.

Or install modellix-agent-canvas, the plugin that ships this one along with the rest of its 3 skills, 2 MCP servers.

Wrote 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.

agentmods badge for modellix-agent-canvas-open

README.md
[![agentmods](https://agentmods.dev/badge/skills/modellix/modellix-agent-canvas/modellix-agent-canvas-open/github.svg)](https://agentmods.dev/skills/modellix/modellix-agent-canvas/modellix-agent-canvas-open)
Your own site
<a href="https://agentmods.dev/skills/modellix/modellix-agent-canvas/modellix-agent-canvas-open"><img src="https://agentmods.dev/badge/skills/modellix/modellix-agent-canvas/modellix-agent-canvas-open/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.

agentmods 80×15 button for modellix-agent-canvas-open

Your own site · 80×15
<a href="https://agentmods.dev/skills/modellix/modellix-agent-canvas/modellix-agent-canvas-open"><img src="https://agentmods.dev/badge/skills/modellix/modellix-agent-canvas/modellix-agent-canvas-open.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 378 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00378
Opus 5 $0.00027 $0.00189
Sonnet 5 $0.00011 $0.00076
Haiku 4.5 $0.00005 $0.00038

Measured 10d ago against content hash 1256b36b3caf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

modellix-agent-canvas-open 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 10d 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.

.agents/skills/modellix-agent-canvas-open/SKILL.md · 16 lines

What it actually says

Open Modellix Agent Canvas

  1. Call get_modellix_canvas_status with refresh: true and the host's active project root as the absolute workspacePath. Use only the current workspace supplied by the host; never guess or browse for another path.
  2. If workspaceBound is false, retry once with the confirmed active project root. Hosts that cannot provide it must restart the MCP with that directory as --project-dir.
  3. Call open_modellix_canvas with the same confirmed workspacePath. Codex and Cursor normally render the MCP Apps widget. Claude Code and OpenCode normally return a short-lived localUrl; tell the user to open it in the same machine's browser.
  4. If credentialState is not valid, tell the user to enter the Key in the isolated credential field displayed directly inside Canvas. The user can create a production key at https://www.modellix.ai/console/api-key. Never request the Key in chat or pass it as an MCP argument. Only if the host cannot display or open Canvas, call start_modellix_api_key_setup and provide its short-lived local URL as recovery.
  5. When the user asks to resume work, call list_modellix_canvas_tasks, then query the relevant nonterminal task IDs with get_modellix_image_task. Finalize successful tasks with finalize_modellix_image_task.

All image generation and editing uses Modellix. Do not inspect or call a host-native image-generation capability.

Changes

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.

  1. 10d ago First seen · 16 lines · 54 tokens per session scan A 1256b36b3caf

Subscribe to this mod's changes

modellix-agent-canvas-open is a skill published in the GitHub repository Modellix/modellix-agent-canvas (0 stars, last pushed 29d ago), licensed MIT. It adds 54 tokens to every session and 378 once invoked, about $0.0003 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.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens