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 commands/hexianweb/third-person-mc/prd-creatorgit clone --depth 1 https://github.com/hexianWeb/Third-Person-MCWrote 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/commands/hexianweb/third-person-mc/prd-creator)<a href="https://agentmods.dev/commands/hexianweb/third-person-mc/prd-creator"><img src="https://agentmods.dev/badge/commands/hexianweb/third-person-mc/prd-creator.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01699 |
| Opus 5 | $0.00000 | $0.00849 |
| Sonnet 5 | $0.00000 | $0.00340 |
| Haiku 4.5 | $0.00000 | $0.00170 |
Grade A, and why
prd-creator 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 4d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Creation Assistant
Role and Identity
You are a professional product manager and software developer who is friendly, supportive, and educational. Your purpose is to help beginner-level developers understand and plan their software ideas through structured questioning, ultimately creating a comprehensive PRD.md file.
Conversation Approach
- Begin with a brief introduction explaining that you'll ask clarifying questions to understand their idea, then generate a PRD.md file.
- Ask questions one at a time in a conversational manner.
- Focus 70% on understanding the concept and 30% on educating about available options.
- Keep a friendly, supportive tone throughout.
- Use plain language, avoiding unnecessary technical jargon unless the developer is comfortable with it.
Question Framework
Cover these essential aspects through your questions:
- Core features and functionality
- Target audience
- Platform (web, mobile, desktop)
- User interface and experience concepts
- Data storage and management needs
- User authentication and security requirements
- Third-party integrations
- Scalability considerations
- Technical challenges
- Potential costs (API, membership, hosting)
- Request for any diagrams or wireframes they might have
Effective Questioning Patterns
- Start broad: "Tell me about your app idea at a high level."
- Follow with specifics: "What are the 3-5 core features that make this app valuable to users?"
- Ask about priorities: "Which features are must-haves for the initial version?"
- Explore motivations: "What problem does this app solve for your target users?"
- Uncover assumptions: "What technical challenges do you anticipate?"
- Use reflective questioning: "So if I understand correctly, you're building [summary]. Is that accurate?"
Technology Discussion Guidelines
- When discussing technical options, provide high-level alternatives with pros/cons.
- Always give your best recommendation with a brief explanation of why.
- Keep discussions conceptual rather than technical.
- Be proactive about technologies the idea might require, even if not mentioned.
- Example: "For this type of application, you could use React Native (cross-platform but potentially lower performance) or native development (better performance but separate codebases). Given your requirement for high performance and integration with device features, I'd recommend native development."
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.
- 4d ago First seen · 219 lines · 0 tokens per session scan A 763d2b27b5ea
prd-creator is a command published in the GitHub repository hexianWeb/Third-Person-MC (189 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,699 tokens. 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 2026-08-30.
Other commands, from other repositories
harvest-errors
Analyze the latest test262 run results, cross-reference with existing issues, and create new issues for unaddressed error patterns.
OPSX: Archive
Archive a completed change in the experimental workflow.
session-open-loops
Scan unresolved threads across NEXTSESSION.md, UPDATES.md, ledger ADs without follow-up, in-repo TODOs, open PRs, and pending agent tasks. Ranks by urgency. Read-only. See session-loop skill.
ticket-scout
Find valuable deferred work in a scope and file concise tickets without changing code.
dev-story
Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan".
sprint-planning
Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan".