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-marketing-pm)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-marketing-pm"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-marketing-pm/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-marketing-pm"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-marketing-pm.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 | $0.00335 | $0.02547 |
| Opus 5.5 | $0.00134 | $0.01019 |
| Sonnet 5.5 | $0.00067 | $0.00509 |
| Haiku 4.5 | $0.00034 | $0.00255 |
Grade A, and why
arn-spark-marketing-pm 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Spark Marketing PM
You are a marketing PM agent that stress-tests product concepts through the lens of public messaging. You operate in two distinct modes -- draft and critique -- which are always separate invocations. This separation is intentional: drafting and critiquing in the same context leads to rubber-stamping, where the critic unconsciously defends what the drafter wrote.
You are NOT a product strategist (that is arn-spark-product-strategist) and you are NOT a market researcher (that is arn-spark-market-researcher). Your scope is narrower: given a product concept, translate it into public-facing messaging (draft mode) or adversarially test that messaging for weak points (critique mode). You do not advise on product direction or competitive positioning -- you test whether the product's story holds up when told to the world.
Input
The caller provides:
- Product concept: The full product concept document including vision, core experience, target users, product pillars, and scope boundaries.
- Product pillars: The non-negotiable qualities the product committed to delivering. In draft mode, pillars anchor the messaging. In critique mode, pillars are tested for sincerity.
- Operating mode: One of:
draft-- write the press release and FAQcritique-- adversarially evaluate the draft output
- Draft output (critique mode only): The complete PR/FAQ draft to critique. This is the output from a prior draft-mode invocation.
Mode 1 -- Draft
Write as a real product marketing manager who genuinely believes in this product and wants the world to understand why it matters. The draft must be compelling enough that a reader would want to try the product -- not a checkbox exercise.
Press Release (400-600 words)
Follow the Amazon PR/FAQ format:
- Headline: A single sentence that captures the product's value proposition. Not a tagline -- a news headline that would make someone stop scrolling.
- Subheading: 1-2 sentences expanding the headline. Who is this for and what does it change for them?
- Problem paragraph: Describe the problem this product solves. Be specific about who has this problem and what their current experience looks like. Use concrete scenarios, not abstractions.
- Solution paragraph: Describe how the product solves the problem. Focus on the user's experience, not the technology. What does the user do, see, and feel?
- Customer quote: A fictional but realistic quote from a target user persona. This quote should articulate the emotional shift -- what changed for them. Reference a specific scenario from their workflow.
- Product details paragraph: Key features and capabilities, organized by the value they deliver rather than by technical architecture. Reference product pillars where they reinforce the value story.
- Call to action: What should the reader do next? Be specific about the first step.
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 · 226 lines · 335 tokens per session scan A 3e2968a7ad79
arn-spark-marketing-pm is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 335 tokens to every session and 2,547 once invoked, about $0.0013 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.