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 QuantumByteOSS/quantumbyte --skill business-requirementsgit clone --depth 1 https://github.com/QuantumByteOSS/quantumbyteWrote 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/quantumbyteoss/quantumbyte/business-requirements)<a href="https://agentmods.dev/skills/quantumbyteoss/quantumbyte/business-requirements"><img src="https://agentmods.dev/badge/skills/quantumbyteoss/quantumbyte/business-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/quantumbyteoss/quantumbyte/business-requirements"><img src="https://agentmods.dev/badge/skills/quantumbyteoss/quantumbyte/business-requirements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00121 | $0.00893 |
| Opus 5.5 | $0.00048 | $0.00357 |
| Sonnet 5.5 | $0.00024 | $0.00179 |
| Haiku 4.5 | $0.00012 | $0.00089 |
Grade A, and why
business-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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Requirements
The harness checks the finished app against a list of business requirements and gives a ship / do-not-ship decision. Those requirements live in the app repo as a single JSON file:
_doc/business-requirements.json
It is a JSON array; each entry is one requirement:
{
"id": "no-checkout-when-closed",
"excerpt": "No buying from a closed store.",
"description": "A customer cannot check out when the selected outlet is closed.",
"type": "explicit",
"severity": "critical"
}
Field rules:
id— stable kebab-case slug. Reuse the existing id when editing a requirement (never renumber). Only mint a new kebab-case id for a genuinely new requirement.excerpt— a tiny glance-line, ideally under ~8 words, clearly shorter thandescription.description— the requirement in explain-like-I'm-five language: short sentences, everyday words, as if explaining to someone with zero technical background. Describe what a person or the business experiences — never code, functions, APIs, endpoints, databases, schemas, tables, or frameworks. If you catch yourself naming a technical thing, rephrase it as what the user or business experiences.- Good: "A customer cannot check out when the selected outlet is closed."
- Good: "Loyalty points are only awarded after an order is completed, never when it is cancelled."
- Bad: "The /checkout endpoint validates outlet.is_open before creating the order."
type—"explicit"when the user asked for it directly,"hidden"when it is implied by the product category but not stated (e.g. preventing double rewards, blocking orders to a closed outlet).severity—"critical","high","medium", or"low", by business impact if unmet. Onlycriticalrequirements block the ship gate; the rest surface as warnings.
How to edit (MANDATORY steps)
Requirements are normally auto-derived from _doc/product-overview.md. To make a hand edit
stick — so the next auto-derivation does not overwrite it — you MUST do BOTH:
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.
- 1mo ago First seen · 70 lines · 121 tokens per session scan A 67fd6e1b13b3
business-requirements is a skill published in the GitHub repository QuantumByteOSS/quantumbyte (294 stars, last pushed 2d ago), licensed Apache-2.0. It adds 121 tokens to every session and 893 once invoked, about $0.0005 per session on Opus 5.5. 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
factory-rereview
Re-review a pull request after a push — reconcile the previous review against the new commits, look for new defects the push introduced, then a fresh pass over the whole PR, and finish with a verdict on the PR.
understand-pr
Review a PR the way a seasoned maintainer would — build an independent model before seeing the diff, investigate the implementation and history, verify material claims, and return a concise briefing. Use for any PR review, self-review, or re-review.
herdr-kit-workflows
Set up and operate Herdr Kit safely: install and configure the plugin and Mastra Code integration, manage Review and Work repository scope, open primary repository workspaces, synchronize managers, materialize or dematerialize managed worktrees, and update Herdr Kit settings or shortcuts.
factory-triage
Triage a Factory work item's issue — trace history, understand architecture, diagnose root cause, then advance the stage.
codemod-patterns
This guide helps AI agents efficiently create codemods with optimal performance and consistency.
factory-gitlab-review
Review a GitLab merge request for a Factory work item using brokered source-control tools.