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 davidYichengWei/Agency --skill requirements-clarificationgit clone --depth 1 https://github.com/davidYichengWei/AgencyWrote 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/davidyichengwei/agency/requirements-clarification)<a href="https://agentmods.dev/skills/davidyichengwei/agency/requirements-clarification"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agency/requirements-clarification/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/davidyichengwei/agency/requirements-clarification"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agency/requirements-clarification.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 | $0.00066 | $0.00555 |
| Opus 5 | $0.00033 | $0.00278 |
| Sonnet 5 | $0.00013 | $0.00111 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
requirements-clarification 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 10d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Clarification
This skill creates and fills spec.md sections 1-3 (background, goals, requirements). The goal is to produce a clear, agreed-upon problem statement before any design work begins — sections 4+ are handled by the system-design skill.
Core Principle
The agent should do the research, the user should provide the intent. Only ask the user for information that cannot be derived from the codebase (goals, scope, priorities, business context). For everything else (current state, interfaces, constraints), use the researcher subagent to investigate and fill it yourself. This reduces the burden on the user — they review and adjust your draft rather than answering a long list of questions.
Workflow
- Copy
assets/spec-template.mdtodocs/design-docs/<module>/<feature>/spec.md - Research the codebase to understand the current state, then draft each section
- Ask the user only for human knowledge: why this is needed, what the goals are, what's in/out of scope
- Present sections 1-3 at Gate: Requirements Understanding for approval
The section order (1.1 → 1.3 → 2.1 → 2.2 → 3.1 → 3.2) is a natural progression, but use your judgment — if the user leads with goals, start there.
Common Pitfalls
| Mistake | Why it's wrong | Do this instead |
|---|---|---|
| Asking the user about current implementation | This is derivable from code — wasted user time | Research it yourself with the researcher subagent |
| Only exploring the module the user mentioned | Misses upstream/downstream dependencies, hidden constraints, and related modules | Start from the user's scope but proactively trace dependencies, call chains, and data flows into adjacent modules |
| Asking multiple questions at once | Overwhelms the user, gets shallow answers | One focused question per turn, dig deep before moving on |
| Writing implementation details in requirements | Mixes WHAT with HOW, constrains design prematurely | Requirements describe what the system should do, not how. See examples in the spec template |
| Accepting vague requirements without pushback | "Make it fast" or "add caching" isn't a requirement | Push for specifics: what's the target latency? What problem does caching solve? |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 32 lines · 66 tokens per session scan A 60420b82171d
requirements-clarification is a skill published in the GitHub repository davidYichengWei/Agency (5 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 555 once invoked, about $0.0003 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 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…