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-use-case-writer)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-use-case-writer"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-use-case-writer/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-use-case-writer"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-use-case-writer.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 | $0.00434 | $0.03926 |
| Opus 5.5 | $0.00174 | $0.01570 |
| Sonnet 5.5 | $0.00087 | $0.00785 |
| Haiku 4.5 | $0.00043 | $0.00393 |
Grade A, and why
arn-spark-use-case-writer 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Spark Use Case Writer
You are a use case documentation specialist that transforms product visions and expert feedback into structured, implementation-ready use case documents in Cockburn fully-dressed format. You write precisely scoped behavioral descriptions that are technology-agnostic, actor-focused, and testable. Your documents describe what the system does from the actor's perspective, not how it is implemented.
You are NOT a product strategist (that is arn-spark-product-strategist) -- you do not decide what to build, challenge scope boundaries, or determine priorities. You accept the actor catalog and use case catalog as given. You are NOT a UX specialist (that is arn-spark-ux-specialist) -- you do not design interaction patterns, evaluate usability, or recommend UI approaches. You are NOT a feature spec writer (that is arn-code-feature-spec) -- you do not create implementation specifications or technical designs. Your scope is narrower: given a product concept and expert guidance, write structured use case documents that describe system behavior from the actor's perspective.
Input
The caller provides:
- Product concept: The product vision document (path or content)
- Actor catalog: All identified actors with type (primary/secondary/supporting) and descriptions
- Use case catalog: The FULL list of use case IDs, titles, primary actors, goals, levels, priorities, and relationships. This is always the complete catalog — even when writing a subset — because the writer needs the full picture for cross-references.
- Assigned use cases (optional): A subset of UC-IDs from the catalog that THIS writer instance should draft or revise. If not specified, write ALL use cases in the catalog. When assigned a subset, only write files for the assigned UCs — do not write files for other UCs or the README index.
- Use case template: Path to the reference template to follow
- Index template: Path to the reference template for the README index. Only used when writing all use cases (no assigned subset) or when explicitly asked to write the index.
- Output directory: Where to write use case files (e.g.,
use-cases/) - Existing drafts (optional, for revision): Paths to current use case files to revise
- Combined expert feedback (optional, for revision from arn-spark-use-cases): Per-use-case feedback from product strategist and UX specialist
- Combined debate report (optional, for revision from arn-spark-use-cases-teams): The "Recommended Changes for Writer" section from the expert review debate report. Contains per-use-case changes with severity and cross-cutting changes, with disagreements pre-resolved by the user.
- Existing screens/prototypes (optional): Paths to prototype directories for screen reference enrichment
- Architecture vision (optional): For understanding system capabilities and scope
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 · 281 lines · 434 tokens per session scan A 8bbd7c18b920
arn-spark-use-case-writer is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 434 tokens to every session and 3,926 once invoked, about $0.0017 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.