A generator for a requirements table covering qualities a system needs beyond its features, such as security, privacy, availability, and performance. It fills the table from a shared YAML reference and filters it by system tier and project type.

Use it to prepare a non-functional requirements table for a high-level design, optionally limited to areas such as privacy or payment security. It can include prompts for supporting evidence.

It gives a design document a consistent starting list of requirements instead of relying on someone to remember them.

nfr-capture — Skill for Claude Code by DavidROliverBA

Install

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.

Any agent

npx skills add DavidROliverBA/ArchitectKB --skill nfr-capture

Clone the repo

git clone --depth 1 https://github.com/DavidROliverBA/ArchitectKB

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/davidroliverba/architectkb/nfr-capture/github.svg)](https://agentmods.dev/skills/davidroliverba/architectkb/nfr-capture)

Your own site

<a href="https://agentmods.dev/skills/davidroliverba/architectkb/nfr-capture"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/nfr-capture/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/davidroliverba/architectkb/nfr-capture"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/nfr-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,652 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00024	$0.02652
Opus 5	$0.00012	$0.01326
Sonnet 5	$0.00005	$0.00530
Haiku 4.5	$0.00002	$0.00265

Measured 9d ago against content hash 04c5a06ce9c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

nfr-capture 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 9d 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.

.claude/skills/nfr-capture/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/nfr-capture

Generate a pre-populated NFR requirements table for a system's HLD, filtered by classification tier and project type. Reads from the NFR-as-Code YAML single source of truth.

Usage

/nfr-capture ERPSystem
/nfr-capture ERPSystem CS2
/nfr-capture "AlertHub" CS1 all,gdpr
/nfr-capture DataPlatform CS2 all,pci,gdpr confluence
/nfr-capture ERPSystem CS2 all,gdpr markdown with-evidence-prompts
/nfr-capture ERPSystem CS2 all,gdpr markdown from-hld:664765269

Data Source

All NFR data is read from .claude/data/nfr-reference.yaml — the single source of truth for all 66 NFRs. Do NOT hard-code NFR content; always read from the YAML.

Instructions

Phase 1: Read NFR Data

Read .claude/data/nfr-reference.yaml
Parse the YAML to extract all sections, NFRs, scoping questions, and archetypes
Note the classification tiers from classification_tiers

Phase 2: Determine System Classification

Option A: Direct arguments — If tier and types are provided, use them.

Option B: Scoping questionnaire — If arguments are omitted, offer the user a choice:

Quick scoping — ask the 6 plain-English questions from scoping_questions in the YAML. Map answers to tier and types using the maps_to fields.
Archetype selection — show the archetypes from archetypes in the YAML and let the user pick one.
Manual selection — show the tier/type selection tables (original behaviour).

If only tier is omitted, show the tier selection table:

What is the Criticality / Service Level tier for [system]?

| Tier | Criticality | Availability | RTO | RPO |
|------|-------------|-------------|-----|-----|
| CS1/SL1 | Critical | 99.95% | 4 hours | Zero data loss |
| CS2/SL2 | High | 99.50% | 8 hours | 1 hour |
| CS3/SL3 | Medium | 99.00% | 5 working days | 1 day |
| CS4/SL4 | Low | 98.50% | 10 working days | 5 days |

If only types is omitted, show the type selection:

Which project types apply to [system]? (select all that apply)

- [ ] All Projects (mandatory baseline)
- [ ] PCI — system handles payment card data
- [ ] GDPR — system processes personal data of UK/EEA subjects
- [ ] CAA/NIS — system supports essential aviation services

Read the full file on GitHub · 267 lines

Changes

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.

9d ago First seen · 267 lines · 24 tokens per session scan A 04c5a06ce9c8

Subscribe to this mod's changes

nfr-capture is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 2,652 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 2026-08-30.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens