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 douglance/sdlc-plugin --skill requirements-gatheringgit clone --depth 1 https://github.com/douglance/sdlc-pluginWrote 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/douglance/sdlc-plugin/requirements-gathering)<a href="https://agentmods.dev/skills/douglance/sdlc-plugin/requirements-gathering"><img src="https://agentmods.dev/badge/skills/douglance/sdlc-plugin/requirements-gathering.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 5.1 | $0.00028 | $0.00748 |
| Opus 5 | $0.00014 | $0.00374 |
| Sonnet 5 | $0.00006 | $0.00150 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
requirements-gathering 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 6d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use lifecycle-documentation only when the result needs a durable artifact or handoff.
Run the relentless interrogation from the interrogate skill against the requirements until the work is unambiguous — one question at a time, a recommended answer for each, exploring the codebase instead of asking when you can.
One twist: you can't reach the user — so address your questions to the main thread. Answer everything you can yourself from the codebase; return the rest as questions for the main thread to resolve or escalate.
When requirements accumulate exceptions or depend on a contested mental model, run find-simplifying-insight before freezing the specification. A simpler model is acceptable only when it preserves observed facts and survives a stated falsification test.
How to interrogate
- Falsify every requirement — probe reversibility, edge cases, scale, security, and internal contradictions. Try to break the requirement, not confirm it.
- Separate functional from nonfunctional — for each capability, pin the quality-of-service targets (latency, throughput, availability, security) and make them measurable, not adjectives.
- Explore before asking — if a question can be answered by reading the codebase, read it instead of asking.
- Cite repository evidence — support every claim about current behavior, conventions, constraints, or feasibility with exact
path:linereferences. Do not cite a whole file when specific lines establish the point. - Find concrete prior art — for each substantial requirement, identify the closest existing implementation and cite the relevant lines. State what transfers, what does not, and why. If no analogue exists, show the searches or commands used and state that the requirement is precedent-free.
- Distinguish reasoning layers — label observations, inferences, and recommendations. An inference must name the evidence it depends on; a recommendation must state the trade-off it resolves.
- Use external prior art selectively — when an argument depends on framework behavior, standards, research, or ecosystem practice, cite a current primary source with its version or publication date. Repository evidence remains authoritative for what this system actually does.
- Sharpen fuzzy language — when a term is vague or overloaded, propose a precise canonical term.
- Record decisions — capture resolved terms and decisions in CONTEXT.md / ADRs as they crystallise.
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.
- 6d ago First seen · 50 lines · 28 tokens per session scan A fb190703ec6e
requirements-gathering is a skill published in the GitHub repository douglance/sdlc-plugin (4 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 748 once invoked, about $0.0001 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…