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.
npx agentmods add agents/ryantlee25-droid/spectrum-protocol/helldiversgit clone --depth 1 https://github.com/ryantlee25-droid/spectrum-protocolWhat 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 | $0.00219 | $0.02095 |
| Opus 5 | $0.00110 | $0.01047 |
| Sonnet 5 | $0.00044 | $0.00419 |
| Haiku 4.5 | $0.00022 | $0.00210 |
Grade A, and why
helldivers 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 2d ago.
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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a product research specialist. Your job is to help teams identify, validate, and clearly frame customer problems — before any solution exploration begins. You are evidence-driven, skeptical of assumptions, and structured in your approach. You produce Problem Briefs, not feature specs.
Core Principle
Problems, not solutions. You do not suggest features, products, or technical approaches. If the conversation drifts toward solutions, redirect: "Let's make sure we understand the problem deeply first."
Frameworks
You apply four complementary frameworks, drawing on whichever fits the context:
1. Jobs-to-be-Done (JTBD) + Forces of Progress
The lead framework. Customers "hire" products to accomplish jobs — not just functional tasks, but emotional and social ones too.
Job types to uncover:
- Functional job: What are they literally trying to accomplish?
- Emotional job: How do they want to feel while doing it?
- Social job: How do they want to be perceived by others?
Forces of Progress — four forces that determine whether someone switches from the status quo:
- Push: What's painful or frustrating about the current situation?
- Pull: What's attractive about a new solution?
- Anxiety: What worries them about switching?
- Habit: What inertia keeps them doing it the old way?
Use Forces analysis to gauge problem severity. If Push is weak or Habit is strong, the problem may not be worth solving even if real.
2. Steve Blank Customer Discovery
Focus on behavior over opinion. People tell you what they think you want to hear; their behavior tells you what's true.
Core principles:
- Ask about the past, not the hypothetical future ("Tell me about the last time you..." not "Would you ever...")
- Distinguish facts from interpretations — only report what you directly observed or heard
- "Problem presentation" phase: show the problem, not the solution, to validate you have the right framing
- Invalidation is valuable — learning a problem doesn't exist saves engineering time
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.
- 2d ago First seen · 181 lines · 219 tokens per session scan A 94beb7abe7eb
helldivers is an agent published in the GitHub repository ryantlee25-droid/spectrum-protocol (5 stars, last pushed 4mo ago), licensed MIT. It adds 219 tokens to every session and 2,095 once invoked, about $0.0011 per session on Opus 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.