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 skills add canvora/canvora-mcp --skill visual-refreshgit clone --depth 1 https://github.com/canvora/canvora-mcpWrote 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/canvora/canvora-mcp/visual-refresh)<a href="https://agentmods.dev/skills/canvora/canvora-mcp/visual-refresh"><img src="https://agentmods.dev/badge/skills/canvora/canvora-mcp/visual-refresh/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/canvora/canvora-mcp/visual-refresh"><img src="https://agentmods.dev/badge/skills/canvora/canvora-mcp/visual-refresh.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 | $0.00055 | $0.01146 |
| Opus 5.5 | $0.00022 | $0.00458 |
| Sonnet 5.5 | $0.00011 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
visual-refresh 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refining what already exists
The most expensive mistake with Canvora is regenerating. A new generation costs
full price, throws away a design the user already liked, and comes back
different in ways they didn't ask for. Almost every "can you change X" is a
3-credit edit. The generate loop and credits: see the canvora skill.
Pick the right operation
| The user says | Tool | Cost |
|---|---|---|
| "make the headline bigger", "change 73% to 78%", "warmer colors", "move the logo" | edit_image on one visual |
3 |
| "same thing in Spanish" | localize_generation |
10 per visual per language |
| "show me some other options" | create_variation |
10 per image (15 per carousel slide) |
| "go back to the previous one" | revert_edit |
free |
| "what did we change?" | get_edit_history |
free |
| "completely different message" | a new generation | full price: the only honest case |
If you're unsure between an edit and variations: does the user want this design fixed, or a different design? Fixed → edit. Different → variations.
To find the visual: get_generation (omit the ID for the most recent one)
lists each output, numbered, with its format and image URL.
Targeted edits
edit_image is two steps:
- Call it with
operationandinstruction, and point at the visual with its image URL assource_image_url(orformatwhen the user names a platform, e.g."instagram_post"). It returns Canvora's edit plan and spends nothing. - Show the user the plan. Then call again with
confirmed: trueand theconfirmed_instructionfrom step 1.
| Operation | Covers |
|---|---|
text |
change, fix, translate, resize or restyle text |
colour |
colours, background, gradients, theme |
layout |
move, resize, align or remove elements, spacing, decorative shapes or icons |
brand |
add, move or replace the logo; apply brand colours or fonts |
- One change per edit. "Bigger headline and make it blue" is two edits, and each preserves more of the design than a combined instruction would.
- Be concrete: name which text or which element. A vague instruction comes back asking for clarification.
- Changes to what the image depicts (the subject, people, products, the scene) aren't available through this connector; the edit comes back with a link to the Canvora editor. Share the link rather than trying another route.
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 Changed · -10 lines d890f7000add
- 2mo ago First seen · 108 lines · 55 tokens per session scan A dae6a2ba8450
visual-refresh is a skill published in the GitHub repository canvora/canvora-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 1,146 once invoked, about $0.0002 per session on Opus 5.5. 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
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
add-pattern
Use this skill when you learn one or more design pattern(s) in the Langroid (multi) agent framework, and want to make a note for future reference for yourself. Use this either autonomously, or when asked by the user to record a new pattern.
patterns
Design patterns for the Langroid multi-agent LLM framework. Covers agent configuration, tools, task control, and integrations.
windows-desktop-control
Use this plugin when the task involves native Windows desktop apps or browser surfaces that do not have a stronger structured integration available.
starknet-agentic-skills
Routes Starknet agent, wallet, DeFi, identity, SDK, and Cairo contract work to the smallest focused skill module.
guizang-ppt-skill
A skill for creating presentation decks as single HTML files that users can move through horizontally in a browser. It provides templates with WebGL backgrounds, chapter title screens, large data displays, and image grids, in either an editorial or Swiss-style visual direction.