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/lukedj78/dev-flow/rn-add-screennpx skills add lukedj78/dev-flow --skill rn-add-screengit clone --depth 1 https://github.com/lukedj78/dev-flowWrote 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/lukedj78/dev-flow/rn-add-screen)<a href="https://agentmods.dev/skills/lukedj78/dev-flow/rn-add-screen"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/rn-add-screen.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 | $0.00170 | $0.02606 |
| Opus 5 | $0.00085 | $0.01303 |
| Sonnet 5 | $0.00034 | $0.00521 |
| Haiku 4.5 | $0.00017 | $0.00261 |
Grade A, and why
rn-add-screen 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 4d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rn-add-screen — add a new screen to a scaffolded RN/Expo app
Contract
See references/contracts.md (vendored from dev-flow). Key facts:
- Reads
<project-root>/.workflow/meta.json#stack.framework— must be"expo-rn". - Requires
meta.json#phase ≥ "scaffolded"(runrn-bootstrapfirst). - Reads
DESIGN.mdfrom project root for the design tokens. - Writes ONE new file under
<project-root>/app/...per call — routes only: Expo Router treats every file underapp/as a route, so nothing else may live there. Optional: screen-private components under<project-root>/components/<feature>/(L0, OUTSIDEapp/— see Folder structure rules below), hooks under<project-root>/lib/queries/. - Sets
meta.json#phase = "page_generated"after the first screen, then leaves it (subsequent screens are stillpage_generated). - Always idempotent: re-adding the same route detects the existing file and reports.
When this skill applies
- Phase is
scaffoldedorpage_generated. - The user describes a screen: name, content, behavior. Or provides a screenshot/wireframe to translate.
- Orchestrator routes here from
dev-flow.
Knowledge dependencies (read these first)
rn-fundamentals/SKILL.md— file layout, modern primitives.rn-styling/references/patterns.md— root screen pattern, dark mode, FlashList.rn-expo-router/references/concepts.md— file-based routing rules.rn-expo-router/references/patterns.md— modal vs push, search params, auth gates.rn-data-fetching/references/patterns.md— if the screen fetches data, use the patterns there.rn-components-apis/references/decision-tree.md— which primitive (FlashList vs ScrollView, Pressable, etc.).
Workflow
Step 1 — Verify preconditions
Read .workflow/meta.json. Abort with clear message if:
stack.framework != "expo-rn"→ "Wrong stack."phase < "scaffolded"→ "Run rn-bootstrap first."
Step 2 — Understand the screen
Gather from user (one round-trip max — collect everything at once):
What ships with it
4 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.
- 4d ago First seen · 145 lines · 170 tokens per session scan A a032a2d51ea0
rn-add-screen is a skill published in the GitHub repository lukedj78/dev-flow (6 stars, last pushed today), licensed MIT. It adds 170 tokens to every session and 2,606 once invoked, about $0.0009 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
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.
ux-design
Create comprehensive UX design with user flows, wireframes, and design systems.
moai-domain-frontend
Frontend development specialist covering React 19, Next.js 16, Vue 3.5, and modern UI/UX patterns with component architecture. Use when building web UIs, implementing components, optimizing frontend performance, or integrating state management.
from-intake
다른 워크스페이스에서 넘겨받은 자료에서 브랜드 근거를 뽑아 에셋에 반영한다.
kirby-panel-and-blueprints
Designs Kirby blueprints and Panel UI, including blueprint reuse/extends, programmable blueprints, and custom Panel fields/sections/areas. Use when changing the Panel experience or schema.
accessibility-fundamentals
Reviews accessibility including WCAG, ARIA, keyboard navigation. Use when junior builds forms, buttons, modals, interactive elements, or asks "is this accessible", "a11y", "screen reader".