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.
curl -O https://raw.githubusercontent.com/Modellix/modellix-agent-canvas/main/.agents/skills/modellix-agent-canvas-image-edit/SKILL.mdgit clone --depth 1 https://github.com/Modellix/modellix-agent-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/modellix/modellix-agent-canvas/modellix-agent-canvas-image-edit)<a href="https://agentmods.dev/skills/modellix/modellix-agent-canvas/modellix-agent-canvas-image-edit"><img src="https://agentmods.dev/badge/skills/modellix/modellix-agent-canvas/modellix-agent-canvas-image-edit/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/modellix/modellix-agent-canvas/modellix-agent-canvas-image-edit"><img src="https://agentmods.dev/badge/skills/modellix/modellix-agent-canvas/modellix-agent-canvas-image-edit.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 | $0.00044 | $0.00507 |
| Opus 5 | $0.00022 | $0.00253 |
| Sonnet 5 | $0.00009 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
modellix-agent-canvas-image-edit 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.
What it actually says
Edit images in Modellix Agent Canvas
Use the Modellix Canvas MCP task tools. Never pass arbitrary local paths or remote image URLs, and never select a provider model slug yourself.
- Call
get_canvas_contextand obtain project-local image business object IDs. Preserve user order, make the first image the explicit primary reference, remove content duplicates while keeping the first occurrence, and use at most 10 images. - For annotation editing, flatten the selected source image, arrows, shapes, strokes, and text with safety padding into a project asset. Keep the source image and every annotation unchanged.
- Call
get_modellix_canvas_statuswithrefresh: true; if required, open Canvas and let the user configure the Key in its embedded isolated credential field. Usestart_modellix_api_key_setuponly when the host cannot display or open Canvas. - Call
prepare_modellix_image_taskwithmode: edit, orderedsourceObjectIdsand/or projectsourceAssetIds, a non-empty prompt, requested size/fit/quality/background/fidelity, count from 1 through 4, activepageId, and the primary image astargetObjectId. - Prepare is non-paying. Show the actual model, route reason, primary/reference count, effective specification, every warning, output count, unit/total estimate, currency, and expiry.
- After explicit confirmation, submit the unchanged intent with a fresh
operationId, returnedrouteFingerprint, andconfirmedPaidSubmission: true. - Poll and immediately finalize successful tasks. Report partial failures independently. Never resubmit an unknown outcome; recover it from
list_modellix_canvas_tasks. - Finalization must preserve, not move, hide, delete, or overwrite source images and annotations. Results go to the right in a stable grid unless the confirmed target is an AI image holder.
For ordinary single-image editing, the default route is GPT Image 2 Edit. Transparent, strict-fidelity, and standard multi-reference requests use a compatible GPT Image 1.5 Edit route; multi-reference special-ratio or 2K/4K requests can route to Nano Banana Pro Edit. Treat the prepare response as authoritative.
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.
- 10d ago First seen · 21 lines · 44 tokens per session scan A 825f3a1900ec
modellix-agent-canvas-image-edit is a skill published in the GitHub repository Modellix/modellix-agent-canvas (0 stars, last pushed 29d ago), licensed MIT. It adds 44 tokens to every session and 507 once invoked, about $0.0002 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 skills, from other repositories
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…