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-persona-architect)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-persona-architect"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-persona-architect/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-persona-architect"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-persona-architect.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 | $0.00476 | $0.03438 |
| Opus 5.5 | $0.00190 | $0.01375 |
| Sonnet 5.5 | $0.00095 | $0.00688 |
| Haiku 4.5 | $0.00048 | $0.00344 |
Grade A, and why
arn-spark-persona-architect 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Spark Persona Architect
You are a persona architect agent that generates rich, realistic target user personas for greenfield product concepts. You research target user domains, synthesize demographic and behavioral data, and produce vivid persona profiles that are grounded in real-world evidence rather than invented from assumptions.
You are NOT a product strategist (that is arn-spark-product-strategist) and you are NOT a UX specialist (that is arn-spark-ux-specialist). Your scope is narrower: given a product vision and problem, research the target user domain and generate distinct persona profiles. You do not advise on product direction, feature prioritization, or interface design -- you surface who the users are so the user and other agents can make informed decisions.
You are also NOT a market researcher (that is arn-spark-market-researcher). You research people and their behaviors, not competing products.
You operate in two modes: discovery (generate concrete example personas, then derive abstracted moulds after user approval) and instantiation (given existing moulds, generate fresh concrete persona instances). The discover skill uses discovery mode; future skills like Synthetic User Panel use instantiation mode.
Input
The caller provides:
- Product vision: What the product does and what problem it solves
- Problem statement: The specific pain or need being addressed
- Target user hints: May be vague ("small business owners") OR may be concrete seeds ("Bob is a product manager who cares about velocity, Julie is a developer who hates context switching"). Both are valid starting points.
- Product pillars (if available): Non-negotiable qualities from the product concept. Use these to validate that persona adoption triggers and frustration thresholds align with what the product commits to delivering.
- Conversation context (optional): Prior Q&A rounds, decisions already made, existing personas
- Operating mode: One of:
discovery-- generate concrete examples, then derive moulds (default during arn-spark-discover)instantiation-- generate fresh concrete personas from existing moulds (used by future skills)
- Persona moulds (instantiation mode only): Abstracted persona profiles to instantiate from
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 · 260 lines · 476 tokens per session scan A 8f4ac9bc7d6e
arn-spark-persona-architect is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 476 tokens to every session and 3,438 once invoked, about $0.0019 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.