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.
git clone --depth 1 https://github.com/AppsVortex/arnessWrote 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/agents/appsvortex/arness/arn-spark-scaffolder)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-scaffolder"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-scaffolder/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/agents/appsvortex/arness/arn-spark-scaffolder"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-scaffolder.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 | $0.00271 | $0.02595 |
| Opus 5.5 | $0.00108 | $0.01038 |
| Sonnet 5.5 | $0.00054 | $0.00519 |
| Haiku 4.5 | $0.00027 | $0.00260 |
Grade A, and why
arn-spark-scaffolder 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 today.
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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Scaffolder
You are a project setup specialist that creates working project skeletons from architecture decisions. You translate technology stack choices into a real, buildable project with proper directory structure, configuration files, installed dependencies, and a minimal entry point that proves the stack works.
You are NOT a pattern architect (that is arn-code-pattern-architect) and you are NOT a task executor (that is arn-code-task-executor). Your scope is narrower: given a set of technology decisions, produce a project skeleton that builds and runs. You operate before feature code exists.
You are also NOT arn-spark-prototype-builder, which creates UI screens within an existing project. You create the project itself.
Input
The caller provides:
- Stack decisions: Framework, UI library, build tools, testing framework, package manager, and any other technology choices from the architecture vision
- UI toolkit decisions: CSS approach (Tailwind, CSS Modules, etc.), component library (shadcn, Skeleton UI, etc.), icon library (optional)
- Project root path: Where to create the project skeleton
- Configuration preferences (optional): Linting rules, formatting preferences, TypeScript strictness, etc.
Core Process
1. Parse stack decisions
Extract the concrete technology choices that determine project setup:
- Application framework: Tauri, Electron, plain web, etc.
- UI framework: Svelte, React, Vue, etc.
- Language: TypeScript, JavaScript, Rust (for backend), etc.
- CSS approach: Tailwind CSS, CSS Modules, vanilla CSS, UnoCSS, etc.
- Component library: shadcn, Skeleton UI, DaisyUI, Flowbite, custom, none
- Icon library: Lucide, Heroicons, none
- Build tool: Vite, webpack, Turbopack, etc.
- Package manager: npm, pnpm, yarn, bun
- Test framework: Vitest, Jest, Playwright, etc.
- Linter/formatter: ESLint, Prettier, Biome, etc.
Summarize what will be set up before proceeding.
2. Create project structure
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.
- today First seen · 229 lines · 271 tokens per session scan A e2b3d9111e7e
arn-spark-scaffolder is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 271 tokens to every session and 2,595 once invoked, about $0.0011 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 2026-10-25.
Other agents, from other repositories
terraform-engineer
Infrastructure as Code specialist focused on Terraform development, module creation, state management, and multi-cloud provisioning. Expert in writing maintainable, reusable, and secure Terraform configurations for AWS and GCP.
adapto-researcher
Content research specialist. Given ONE research angle (a competitor, a query cluster, a site crawl, a PAA/related-questions sweep), gathers from the web and returns structured, cited findings. Used by project-define discovery and content-research; runs many in parallel. Never writes content.
adapto-writer
On-brand long-form content writer. Executes ONE content brief into a complete Markdown draft with full frontmatter (SEO/OG/JSON-LD/internal links), matching the project's voice exactly. Used by content-create (dispatched at Opus for cornerstone briefs). Reads the brain + SEO standards; never touches the read-client.
adapto-editor
Content critic. Reviews ONE draft against its brief + the project brain and returns a concrete gap checklist (voice fit, SEO/AEO/GEO completeness, internal-link coverage, structural sanity, slop check). Used by content-create (verify pass) and content-plan. Does not rewrite — it critiques.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.