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 agentmods add skills/lykhoyda/rn-dev-agent/rn-best-practicesnpx skills add Lykhoyda/rn-dev-agent --skill rn-best-practicesgit clone --depth 1 https://github.com/Lykhoyda/rn-dev-agentWrote 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/lykhoyda/rn-dev-agent/rn-best-practices)<a href="https://agentmods.dev/skills/lykhoyda/rn-dev-agent/rn-best-practices"><img src="https://agentmods.dev/badge/skills/lykhoyda/rn-dev-agent/rn-best-practices.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 | $0.00098 | $0.02343 |
| Opus 5 | $0.00049 | $0.01171 |
| Sonnet 5 | $0.00020 | $0.00469 |
| Haiku 4.5 | $0.00010 | $0.00234 |
Grade A, and why
rn-best-practices 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Native Best Practices — Procedural Adapter
This skill is the routing surface between Claude and the vendored
vercel-labs/agent-skills
content under third_party/vercel-labs/agent-skills/. Don't read the 118
rule files upfront. Use the procedures below to look up only the rules
that apply to the code you're about to write or review.
Index
The routing surface is skills/rn-best-practices/rules.index.json. Each entry:
{ "id": "react-native-skills/list-performance-virtualize",
"title": "Use a list virtualizer for any list",
"category": "react-native-skills",
"platform": "RN",
"severity": "CRITICAL" | "HIGH" | "MEDIUM" | "LOW",
"triggers": ["FlatList", "FlashList", "ScrollView"],
"upstream_path": "third_party/vercel-labs/agent-skills/skills/.../list-performance-virtualize.md",
"checkable": true | false,
"checkerRule": "no-touchable-new-code" | null
}
Query with jq or read directly. Filter by platform: "RN" for React Native
work; platform: "both" for composition rules; platform: "web" only for
web React when applicable.
Always check (inline, regardless of category)
These cause runtime crashes. Check on every review pass. Do not delegate.
Falsy-&& rendering crash
{x && <Comp />} where x could be 0, "", or NaN renders the falsy
value as a string in RN. Bad: {count && <Badge />} (renders "0").
Good: {count > 0 && <Badge />} or ternary. Full rule:
third_party/vercel-labs/agent-skills/skills/react-native-skills/rules/rendering-no-falsy-and.md
Bare strings outside <Text>
A string as a direct child of <View> is a runtime crash on RN.
Bad: <View>Hello</View>. Good: <View><Text>Hello</Text></View>.
Full rule: .../rules/rendering-text-in-text-component.md
Components defined inside components
Defining const Child = () => … inside function Parent() creates a new
component type every render. RN remounts it, destroying state, native views,
animations, scroll position, focus. Bad: inline function components inside
parents. Good: define outside, pass data via props. Full rule (web/RN):
.../skills/react-best-practices/rules/rerender-no-inline-components.md
What ships with it
5 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.
- 6d ago First seen · 191 lines · 98 tokens per session scan A b26665503050
rn-best-practices is a skill published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 2,343 once invoked, about $0.0005 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.
Other skills, from other repositories
openforms-mui
Author, render, preview and debug OpenForms FormSchemaJSON form definitions as idiomatic, themed, accessible MUI (React). Use when the user wants to design an OpenForms form, render an OpenForms schema with Material UI, convert an OpenForms JSON schema into a React MUI form, preview a form schema, or debug…
skill-packager
Authors Agent Skills v1.0 packages (SKILL.md plus references/scripts), runs packageskill to produce a standards-compliant zip, and uses installskill to add skills from HTTPS, registry, workspace, or an uploaded archive. Use when the user wants to turn documentation, workflows, or code into a portable skill, export a…
data-analyzer
Guidance for analyzing structured data, generating statistics and producing data-driven insights. Use when the user asks to analyze data, compute statistics, find patterns, or generate analytical reports.
document-processor
Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.
workflow-helper
Guidance for creating, managing and executing workflow automations that chain multiple tools and agents together. Use when the user asks about building, listing, running or composing workflows and automated task pipelines.
attendance-signin-sheet
Generate printable attendance / 签到表 spreadsheets from name lists. Use when the user asks for 签到表, attendance sheet, meeting sign-in table, or similar printable roster tables (not full payroll attendance scoring unless asked).