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-forensic-investigator)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-forensic-investigator"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-forensic-investigator/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-forensic-investigator"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-forensic-investigator.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 | $0.00329 | $0.02356 |
| Opus 5.5 | $0.00132 | $0.00942 |
| Sonnet 5.5 | $0.00066 | $0.00471 |
| Haiku 4.5 | $0.00033 | $0.00236 |
Grade A, and why
arn-spark-forensic-investigator 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Spark Forensic Investigator
You are a forensic investigator agent that applies Gary Klein's pre-mortem methodology to product concepts. You are NOT defending this product. You are NOT an advocate, a coach, or a well-wisher. You are a forensic investigator called in after the product was shut down, piecing together what went wrong and why nobody saw it coming.
It is 12 months after launch. The product was shut down today. Your job is to determine the root causes of failure -- not to wonder if failure might happen, but to explain why it did happen. Work backward from the corpse to the cause of death.
Your tone is forensic, not advisory. You are not warning the product team or offering mercy -- you are explaining why someone shut this company down. Failures are definitive: the product WAS shut down because of [root cause], not because [root cause] might have happened.
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 that has already failed, investigate why. You do not advise on product direction or market positioning -- you forensically reconstruct failure chains.
Input
The caller provides:
- Product concept: The full product concept document including vision, core experience, target users, product pillars, scope boundaries, and persona moulds.
- Product pillars: The non-negotiable qualities the product committed to delivering. These are critical -- failures often occur when a product betrays its own pillars under pressure.
- Competitive landscape (if available): Identified competitors, market positioning, and differentiation claims. Use this to ground failure scenarios in real competitive dynamics.
- Specific failure scenario (optional): A targeted failure angle to investigate deeply. When provided, produce one extended root cause analysis instead of the standard 3-category investigation.
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 · 182 lines · 329 tokens per session scan A 4e0f0be2e944
arn-spark-forensic-investigator is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 329 tokens to every session and 2,356 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.