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.
git clone --depth 1 https://github.com/MohammadShehadeh/agent-skillsWrote 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/commands/mohammadshehadeh/agent-skills/new-component)<a href="https://agentmods.dev/commands/mohammadshehadeh/agent-skills/new-component"><img src="https://agentmods.dev/badge/commands/mohammadshehadeh/agent-skills/new-component/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/commands/mohammadshehadeh/agent-skills/new-component"><img src="https://agentmods.dev/badge/commands/mohammadshehadeh/agent-skills/new-component.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 | $0.00028 | $0.00876 |
| Opus 5 | $0.00014 | $0.00438 |
| Sonnet 5 | $0.00006 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
new-component 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a component: $ARGUMENTS
Load the agent-skills-conventions skill. Think through phases 1–3 before writing any markup.
1. Understand — role before markup
- Place it in the tree: is this a page-level section, a block inside one, or a primitive? It must sit at page → section → primitive depth — if it only forwards props downward, it shouldn't exist.
- Search first: an existing shadcn/ui primitive or house component may already do this. Compose or extend before creating; a new shared primitive is the last resort, only when no shared one fits.
- Enumerate its states up front: default, hover/focus, loading, empty, error, disabled — whichever apply. Every visible state must trace to a prop or state in the design; discovering states mid-build is how boolean props sneak in.
- Name it by business meaning:
MessageRow,PlanCard— notListItem2,Wrapper.
2. Design the props API — before the markup
- Minimal: only the props today's call sites need. No speculative variants, sizes, or flags — the flexibility nobody asked for is the review comment you'll get.
- Composition over configuration:
children/slot props over render-config props; compound components over prop-heavy ones (Card+CardHeader, never<Card header={...} footer={...} />). - Variants are a typed union prop backed by a lookup map or CVA — never a pile of booleans (
isPrimary,isLarge). - State stays with its owner: the component receives values and emits
on*callbacks (onArchive,onSelect); it does not fetch or own state its siblings also need. Booleans readis/has/should; internal handlers arehandle*. - Declare
interface <Component>Props(noIprefix), destructured in the signature;children: React.ReactNodewhen composed.
3. Decide server vs client
- Server component unless it needs interactivity — and then
'use client'at this leaf only, never hoisted. - Animation comes from the
motion.tsxclient boundary; icons import directly from the icon library as component objects (server-safe, no string keys, no sizing classes inside the component).
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 · 44 lines · 28 tokens per session scan A 1febb8045090
new-component is a command published in the GitHub repository MohammadShehadeh/agent-skills (2 stars, last pushed 26d ago), licensed MIT. It adds 28 tokens to every session and 876 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 commands, from other repositories
prototype-loop
Enter leveraged-prototype focus mode — focus marker plus normal watch/rebuild loop for visual-parity work and batch upstream framework gap-fixes.
review-arch
Review the current branch for code quality, TypeScript, and React/Next.js patterns. Supports whole-branch review or scoped review by path, feature, or base branch.
a11y-audit-react
Identify accessibility violations in React components and provide actionable remediation aligned with WCAG 2.2 Level AA. This is the guided audit workflow that applies the standards defined in the a11y-automation and react-components rules.
create-variant
Add a new variant to an existing shadcn/ui component.
react-build
Fix React build failures (Vite, webpack, Next.js, CRA, Parcel, esbuild, Bun) incrementally — JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types. Invokes the react-build-resolver agent for minimal, surgical fixes.
next-upgrade
Structured workflow for upgrading Next.js applications across major versions. Use when migrating a Next.js project from one major version to another (e.g., 13 to 14, 14 to 15, 15 to 16). Covers codemod automation, breaking change detection, incremental migration paths, and post-upgrade validation.