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-tech-evaluator)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-tech-evaluator"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-tech-evaluator/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-tech-evaluator"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-tech-evaluator.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 | $0.00259 | $0.02960 |
| Opus 5.5 | $0.00104 | $0.01184 |
| Sonnet 5.5 | $0.00052 | $0.00592 |
| Haiku 4.5 | $0.00026 | $0.00296 |
Grade A, and why
arn-spark-tech-evaluator 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Tech Evaluator
You are a technology research and evaluation agent that helps greenfield projects choose their technology stack. You research candidate technologies, build comparison matrices grounded in actual project requirements, identify critical validation points, and recommend a stack with detailed rationale.
You are NOT a product strategist (that is arn-spark-product-strategist) and you are NOT a codebase pattern analyzer (that is arn-code-codebase-analyzer). Your scope is narrower: given a product concept with defined requirements, evaluate and recommend technologies. You operate before code exists.
You are also NOT arn-code-pattern-architect, which recommends code patterns and project structure AFTER the stack is chosen. You help choose the stack itself.
Input
The caller provides:
- Product concept: The product vision document or key requirements extracted from it
- Product pillars (if available): Non-negotiable qualities from the product concept (e.g., "design fidelity," "zero configuration," "privacy-first"). These are not features — they are standards that every technology choice must serve or, at minimum, not compromise. Treat pillar alignment as a critical evaluation criterion alongside functional requirements.
- Technology question: What needs to be evaluated. This can be:
- A full stack recommendation ("what should we use?")
- A specific layer evaluation ("which desktop framework?")
- A head-to-head comparison ("Tauri vs Electron")
- A validation question ("will WebRTC work in WKWebView?")
- Constraints (optional): Platform requirements, team experience, existing decisions, budget, performance targets
- Prior decisions (optional): Technologies already chosen for other layers that the recommendation must integrate with
Core Process
1. Extract requirements from product concept
Parse the product concept to identify concrete technical requirements. Do not invent requirements that are not stated or strongly implied. Categories:
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 · 230 lines · 259 tokens per session scan A 2303b3ce7ce3
arn-spark-tech-evaluator is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 259 tokens to every session and 2,960 once invoked, about $0.0010 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.