Borrowing it
Nothing to install: this file belongs to arcasilesgroup/ai-engineering. 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/arcasilesgroup/ai-engineering/main/.agents/skills/ai-visual-plan/SKILL.mdgit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/arcasilesgroup/ai-engineering/ai-visual-plan)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-visual-plan"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-visual-plan.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 5.1 | $0.00134 | $0.00957 |
| Opus 5 | $0.00067 | $0.00478 |
| Sonnet 5 | $0.00027 | $0.00191 |
| Haiku 4.5 | $0.00013 | $0.00096 |
Grade A, and why
ai-visual-plan 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 7d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Render the plan the human has to approve
What it produces
The plan file with its visual blocks, and the page ai-eng report view renders from it:
one self-contained file under .ai/views/, printed in chat as a file:// link beside the
digests of the bytes it was rendered from. The Markdown stays the record; the page is a
reading of it.
Steps
-
Read
policy/visual-pages.mdfirst. It owns the block vocabulary and the editorial bar; if it is absent, stop and restore it before authoring — blocks written from memory are how the shapes drift. -
Research before you decorate. Read the real files, names and data shapes the plan touches, and say what each step reuses before what it adds. A diagram of an architecture nobody checked is the padding this skill exists to remove from chat.
-
Decide which surfaces earn their place: a
diagramfor a flow the prose makes the reader reconstruct, adecision-tablewhere options are being compared, afile-treefor a footprint, oneopen-questionsblock at the end with a recommendation per question. Skip every block whose content the sentence already carries — visual chrome over plain prose is the same noise in a better font. -
Author the blocks inside the plan's Markdown, never beside it. The fence is a wall: a numbered line or a bold field inside a block is content, invisible to the task parser and the approval digest. If the plan is pasted text, save it under
specs/or hand it to/ai-planfirst; a page over bytes nothing tracks is unrevisable. -
Render and show the link:
ai-eng report view --spec <NNN>The command prints the page's path as a
file://link and the digests it rendered. Show both. If the command refuses, fix the bytes it named; never hand-write the HTML. -
Planning stays read-only on source. The page is the approval gate's surface, and the approval itself is the ADR at the digests the page prints — presenting the page and asking for sign-off is the step; do not ask a second "does this look good?".
-
When the direction changes, change the Markdown and re-render. The document is the source of truth; a page that only exists in the chat is a plan nobody can reopen.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 76 lines · 134 tokens per session scan A e0161e97bbf6
ai-visual-plan is a skill published in the GitHub repository arcasilesgroup/ai-engineering (54 stars, last pushed 5d ago), licensed Apache-2.0. It adds 134 tokens to every session and 957 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
ui-ux-design
Create production-grade frontend interfaces with strong UX and visual craft. Use when building web components, pages, dashboards, forms, landing pages, modals, or any UI. Use when user says 'build a form', 'create a dashboard', 'design a component', 'make a landing page', or asks for UI/UX work. Use even when the user…
ndv-perceptual
Perceptual cognition module. Injects simultaneous read-as-rendered vision into any phase where visual or UX quality is a concern — implementation review, component assessment, UI audit steps within a larger workflow. Source: ndv-design (Pixel).
frontend-design
Use this skill when building UI components, designing frontend architecture, implementing styling systems, optimizing performance, ensuring accessibility, or creating production-grade interfaces. Trigger on keywords: frontend, component, UI, styling, React, Next.js, Angular, Tailwind, CSS, responsive, accessibility…
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…