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 AppsVortex/arness/plugin install arn-codeWrote 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/appsvortex/arness/arn-code-sketch)<a href="https://agentmods.dev/skills/appsvortex/arness/arn-code-sketch"><img src="https://agentmods.dev/badge/skills/appsvortex/arness/arn-code-sketch/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/appsvortex/arness/arn-code-sketch"><img src="https://agentmods.dev/badge/skills/appsvortex/arness/arn-code-sketch.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 | $0.00163 | $0.03801 |
| Opus 5.5 | $0.00065 | $0.01520 |
| Sonnet 5.5 | $0.00033 | $0.00760 |
| Haiku 4.5 | $0.00016 | $0.00380 |
Grade A, and why
arn-code-sketch 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 1mo 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Sketch
Create a working interface preview of a feature using the project's actual framework, conventions, and styling system. The sketch renders the new feature in context -- showing it within the real application where it will live, not in isolation. This lets the user see and interact with a preview before committing to the full implementation pipeline.
Sketches are real code: runnable artifacts written with the project's conventions, served from a dedicated arness-sketches/ namespace. They can be iterated on via feedback, promoted into the real codebase, or cleaned up when no longer needed.
This is a conversational skill. It runs in normal conversation (NOT plan mode).
Prerequisites
-
Arness must be configured. Read the project's CLAUDE.md and check for a
## Arnesssection. If missing, inform the user: "Arness is not configured for this project yet. Run/arn-implementingto get started — it will set everything up automatically." Do not proceed without it. -
Sketch strategy must exist. Read
ui-patterns.mdfrom the project's code patterns directory (the path under Code patterns: in the## Arnessconfig). Look for a## Sketch Strategysection. If absent, halt with:"No sketch strategy found. Run
/arn-implementingto get started — pattern documentation will be generated on first use, including the sketch strategy if your project has a UI framework."Do not proceed without a sketch strategy.
Pipeline Position
Entry points:
- Direct: user says "sketch this" / "preview this"
- From feature-spec: proactively offered after initial proposal when UI is involved
- From feature-spec-teams: proactively offered after debate converges when UI is involved
- From swift: after swift assessment, offered for interface changes above threshold
arn-code-sketch (this skill)
=========================
For interface preview before implementation
Input: Feature description (from spec, swift, or direct)
|
v
Load: Sketch strategy + paradigm reference from pattern docs
|
v
Assess: Should this be sketched? (threshold rules)
|
+--- Below threshold --> "This change is small enough to implement
| directly. Proceed with /arn-code-swift or
| /arn-code-feature-spec instead."
|
+--- Above threshold --> Continue
|
v
Create: arness-sketches/[feature-name]/ artifact namespace
|
v
Build: Spawn arn-code-sketch-builder agent
|
v
Present: Show preview instructions, iterate on feedback
|
v
Finish: Promote to real codebase OR clean up
What ships with it
6 files 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.
- 1mo ago First seen · 298 lines · 163 tokens per session scan A 0305c5dd32da
arn-code-sketch is a skill published in the GitHub repository AppsVortex/arness (33 stars, last pushed 2mo ago), licensed MIT. It adds 163 tokens to every session and 3,801 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
agent-reels
Find animation and video references on 1human, consult a human-agent shared library, and contribute public creations only with prior owner permission.
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
shiny-bslib
Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…
ux-heuristics
Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "users are confused", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "is this easy to use". Also trigger when reviewing a design for usability issues, improving…
aws-architecture-diagram
Generate AWS architecture diagrams in draw.io format. Activates when the user asks to create, generate, or build an architecture diagram, system diagram, or draw.io diagram for AWS services.