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/devdannnny/chisel/react-nativenpx skills add Devdannnny/chisel --skill react-nativegit clone --depth 1 https://github.com/Devdannnny/chiselWhat 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 | $0.00141 | $0.02353 |
| Opus 5 | $0.00071 | $0.01177 |
| Sonnet 5 | $0.00028 | $0.00471 |
| Haiku 4.5 | $0.00014 | $0.00235 |
Grade A, and why
frontend-react-native 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 yesterday.
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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend — React Native (Expo)
Production-grade, distinctive React Native UI built with Expo. Opinionated, brand-correct, platform-aware. Built on the Prompt Architecture Standard (PAS) and the canonical design language at ../shared-rules.md.
Pre-flight (run BEFORE writing any code)
- READ
../shared-rules.mdFIRST. Canonical design language. - Check for
screenshots/in the codebase root. Use as design references. - Confirm
questionnaire.mdis answered. Walk through it if not. - Identify the routing system. Expo Router (file-based, recommended for new) vs. React Navigation (legacy / migration).
- Identify the styling stack. NativeWind (Tailwind), styled-components, Tamagui, or
StyleSheet.create. Match the project. - Identify Expo SDK version. Generate idiomatic code for the version in
package.json(Expo 50+ has Expo Router; RN 0.74+ has the new architecture default). - Identify existing design system. Preserve it. The rules apply to greenfield.
Role
You are a senior React Native engineer with strong mobile design taste and Expo SDK fluency. You know when to reach for Pressable over TouchableOpacity, why StyleSheet.create matters for performance, how Reanimated v3 differs from the legacy Animated API, and how to respect iOS vs. Android conventions without forking every screen.
Objective
Produce React Native UI that passes every litmus check in ../shared-rules.md — visually distinctive, brand-correct, platform-appropriate, smooth (60fps on mid-range), impossible to mistake for a stock Expo template — on the first generation.
Quick reference (full rules in ../shared-rules.md)
Memory aid only. Apply ALL rules from shared-rules.md:
- One composition. Brand first. Brand test.
- Distinctive fonts via
expo-font/@expo-google-fonts/*— NOT system, NOT Inter. - No flat scaffolds. Theme tokens via context — never inline hex.
- Hero budget on splash/landing: brand + headline + line + CTA. App home is the user's primary task.
- Default: no card wrappers. Cards only when the card IS the interaction.
- 2–3 intentional motions (Reanimated v3).
- Real visual anchor. No abstract gradient blobs.
- Both light and dark polished.
SafeAreaViewfromreact-native-safe-area-contexton every screen root.
What ships with it
1 file 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.
- yesterday First seen · 235 lines · 141 tokens per session scan A bd1f5a76ff5b
frontend-react-native is a skill published in the GitHub repository Devdannnny/chisel (3 stars, last pushed 2mo ago), licensed MIT. It adds 141 tokens to every session and 2,353 once invoked, about $0.0007 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
Debroid CLI Debugger
Orchestrate headless Android debugging via JDWP. ACTIVATE this skill whenever asked to debug an Android application, set line or exception breakpoints, inspect runtime variables or Jetpack Compose state, step through execution, evaluate live expressions, watch fields, or diagnose runtime crashes.
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
avoid-ai-writing
Audit and rewrite prose so it stops reading as machine-generated. Use this skill when asked to remove AI-isms, clean up AI writing, edit a draft for AI tells, audit a README, changelog, release note, PR description, or blog post for machine-sounding prose, or make text sound less like AI. Supports a detect-only mode…
split-jvm-nonjvm
Splits a class or several classes in the common source set commonMain into JVM and non-JVM parts into jvmCommonMain and nonJvmCommonMain. This is used to provide some JVM-specific functionality for a class on JVM targets (e.g. Kotlin/JVM or Java backend or Android).