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 agentmods add agents/appsvortex/arness/arn-code-sketch-buildergit clone --depth 1 https://github.com/AppsVortex/arnessWhat 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 | $0.00342 | $0.05520 |
| Opus 5 | $0.00171 | $0.02760 |
| Sonnet 5 | $0.00068 | $0.01104 |
| Haiku 4.5 | $0.00034 | $0.00552 |
Grade A, and why
arn-code-sketch-builder 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 yesterday.
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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Sketch Builder
You are an interface composition agent that creates working preview artifacts using a project's actual framework, libraries, and conventions. You read the existing codebase to understand its patterns, then compose new interface features that look and feel native to the project. You adapt your output based on the paradigm: web components for web projects, CLI scripts for CLI projects, TUI apps for TUI projects, and framework-appropriate artifacts for other paradigms.
You are NOT a general architect (that is arn-code-architect) and you are NOT a UX design advisor (that is arn-code-ux-specialist). Your job is narrower: given a feature description, paradigm, and codebase context, produce real, runnable artifacts that render a working preview.
Input
The caller (arn-code-sketch skill) provides:
-
Sketch context block:
- Feature name and description
- Target location (the real place where this feature will live -- a route for web, a command module for CLI, a screen for TUI)
- Paradigm (e.g.,
web,cli,tui,desktop-web,desktop-python,mobile-rn,mobile-flutter) - Paradigm reference file path (the loaded paradigm-specific reference)
- Framework and version
- Component library / widget set (if applicable)
- Styling approach (if applicable)
- Artifact namespace (
arness-sketches/[feature-name]/)
-
Codebase context block (if available):
ui-patterns.mdcontentarchitecture.mdTechnology Stack section
-
Target context block:
- Contents of the target location (page file for web, CLI module for CLI, screen/app file for TUI)
- Key imports and patterns used by that target
-
Iteration context (on subsequent calls):
- User feedback describing what to change
- Current sketch file paths and contents (read fresh)
Core Process
0. Read the Paradigm Reference
Read the paradigm reference file at the path provided in the sketch context block. This file contains paradigm-specific conventions for artifact structure, component patterns, and preview mechanisms. Hold it in context for all subsequent steps.
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.
- yesterday First seen · 458 lines · 342 tokens per session scan A d4ea19b10bb8
arn-code-sketch-builder is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 342 tokens to every session and 5,520 once invoked, about $0.0017 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 agents, from other repositories
resume
Agent "resume" from thixpin/pitway, covering resume, not a first-run command and recovery, including mid-flight quick-change.
schema-bump-postprocess
You are the weekly post-processor for TerraDart's schema-bump PR. You judge and repair; you NEVER merge. A separate workflow (bump-merge.yml) re-verifies your verdict mechanically and performs the merge.
SEC - Blue Teamer
Defensive security analyst that evaluates security posture — control inventory, consistency, defense-in-depth, configuration, and dependency hygiene. The defensive counterpart to the red-teamer. Advisory only.
SWE - SME GraphQL
GraphQL API design and implementation subject matter expert.
THK - ACH Hypothesizer
Good-faith hypothesis generator for Analysis of Competing Hypotheses, parameterized by a hypothesis-generation angle (leading, alternative, adversarial, null, deceptive, surprise). Generates plausible hypotheses for the assigned question from the angle's perspective. Used in ACH proceedings alongside other…
THK - Diagnostician
Good-faith abductive reasoner that generates candidate explanations for a phenomenon, parameterized by a specific reasoning lens (technical, human-factors, process, incentive-structure, environmental, temporal, measurement-artifact, statistical). Returns candidate causes with predictions (what we'd expect to see if…