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 skills add njt/powerups-requirements --skill gathering-requirementsgit clone --depth 1 https://github.com/njt/powerups-requirementsWrote 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/skills/njt/powerups-requirements/gathering-requirements)<a href="https://agentmods.dev/skills/njt/powerups-requirements/gathering-requirements"><img src="https://agentmods.dev/badge/skills/njt/powerups-requirements/gathering-requirements/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/skills/njt/powerups-requirements/gathering-requirements"><img src="https://agentmods.dev/badge/skills/njt/powerups-requirements/gathering-requirements.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 | $0.00163 | $0.02933 |
| Opus 5 | $0.00081 | $0.01466 |
| Sonnet 5 | $0.00033 | $0.00587 |
| Haiku 4.5 | $0.00016 | $0.00293 |
Grade A, and why
gathering-requirements 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 11d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gathering Requirements
Purpose
Extract structured requirements from a human stakeholder's head (and their existing documentation) through iterative questioning. The human has domain knowledge. You have structure. Together you produce a requirements.md and optionally systems.md that an LLM can use to build the thing.
This is the Capture and Challenge phase. The requirements-management skill handles everything after this — maintenance during development, subagent updates, session startup.
Role Division
You do: Ask questions. Listen. Compile. Filter noise from signal. Identify gaps. Draft structured requirements text. Propose open questions for things you can't resolve.
The human does: Supply domain knowledge. Correct your misunderstandings. Answer questions. Provide existing documentation. Confirm or reject your interpretations.
You never: Guess at business rules. Invent requirements the human didn't imply. Assume you understand a domain term without confirming. Skip to implementation.
What Belongs in Requirements
As you extract requirements, continuously filter:
Requirement = behaviour observable from outside. "Display client name in task list." Decision = how the system achieves a requirement. "Store config at ~/.cu/config.json." Style = formatting/presentation. "Truncate names at 45 characters with '...' suffix." Non-Goal = something explicitly rejected. "Font size buttons (old platform constraint, unnecessary on web)." Scenario = a concrete example that illustrates a business rule with specific data. "Given a VIP customer with 5 books in their cart, when they checkout, they should be offered free delivery." Scenarios sit inside their FR — they're not separate artefacts.
The litmus test: "If I changed this, would the user notice a different capability?" If yes → requirement. If no → decision or style.
When extracting from existing code or documentation, implementation details will dominate. Record the user need, not the implementation. See requirements-management skill for the full "Requirements vs Spec vs Style" guide.
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.
- 11d ago First seen · 270 lines · 163 tokens per session scan A c4bf44afbd32
gathering-requirements is a skill published in the GitHub repository njt/powerups-requirements (11 stars, last pushed 5mo ago), licensed MIT. It adds 163 tokens to every session and 2,933 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…