validate-conventions

validate-conventions is a skill for Claude Code from FouadMagdy01/RNCopilot. It costs 12 tokens per session (1,208 once invoked), scanned A, original, MIT.

A checklist for reviewing changed code against the rules in a project's CONVENTIONS.md file. It checks imports, file locations, exports, styling, and other listed conventions.

In plain words
What is it for?
Use it after editing code to inspect changed files and identify violations such as incorrect imports, deep relative paths, inline styles, or wrong export types.
Why use it?
It helps catch project-specific mistakes before code review or testing, especially when the rules differ from standard React Native practices.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it after editing code to inspect changed files and identify violations such as incorrect imports, deep relative paths, inline styles, or wrong export types.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fouadmagdy01/rncopilot/validate-conventions
Install

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.

Any agent
npx skills add FouadMagdy01/RNCopilot --skill validate-conventions
Clone the repo
git clone --depth 1 https://github.com/FouadMagdy01/RNCopilot

Made for: Claude Code.

Wrote 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.

agentmods badge for validate-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/fouadmagdy01/rncopilot/validate-conventions/github.svg)](https://agentmods.dev/skills/fouadmagdy01/rncopilot/validate-conventions)
Your own site
<a href="https://agentmods.dev/skills/fouadmagdy01/rncopilot/validate-conventions"><img src="https://agentmods.dev/badge/skills/fouadmagdy01/rncopilot/validate-conventions/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.

agentmods 80×15 button for validate-conventions

Your own site · 80×15
<a href="https://agentmods.dev/skills/fouadmagdy01/rncopilot/validate-conventions"><img src="https://agentmods.dev/badge/skills/fouadmagdy01/rncopilot/validate-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,208 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.01208
Opus 5 $0.00006 $0.00604
Sonnet 5 $0.00002 $0.00242
Haiku 4.5 $0.00001 $0.00121

Measured 9d ago against content hash 88b31f3fc24a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

validate-conventions 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.

.claude/skills/validate-conventions/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate Conventions

Review changed code against all project conventions defined in CONVENTIONS.md.

Steps

1. Get Changed Files

Run git diff --name-only HEAD to find modified files. If no uncommitted changes, check git diff --name-only HEAD~1 for the last commit.

If the user specifies particular files, use those instead.

2. Read Changed Files

Read each changed file to inspect the code.

3. Check Against Rules

For each file, check ALL of the following rules:

Import Rules
  • StyleSheet imported from react-native-unistyles, NOT react-native
  • Text imported from @/common/components/Text, NOT react-native
  • z imported from zod/v4, NOT zod
  • Path aliases used (@/ or ~/), no deep relative imports (../../..)
  • Import order: React core > third-party > @/ internal > relative
  • Type imports use import type { ... }
  • Imports from barrel files, not implementation files (e.g., @/common/components/Button not @/common/components/Button/Button)
Component Rules
  • Named exports in src/ files
  • Default exports in app/ screen files
  • styles.useVariants() called before accessing styles (if using variants)
  • No inline styles - all styles in StyleSheet.create
  • Accessibility props on all interactive elements:
    • accessibilityRole on Pressable, TouchableOpacity, buttons
    • accessibilityLabel on interactive elements
    • accessibilityState for disabled/busy/selected states
Style Rules
  • StyleSheet.create((theme) => ({...})) pattern with theme callback
  • No color literals (#hex, rgb(), named colors) - use theme.colors.*
  • No hardcoded numeric spacing - use theme.metrics.spacing.* or theme.metrics.spacingV.*
  • No hardcoded font sizes - use theme.fonts.size.*
  • No hardcoded border radius - use theme.metrics.borderRadius.*
State Management Rules
  • Zustand stores accessed with selectors: useStore((s) => s.field), NOT useStore()
  • No useAuthStore() without selector
  • No useAuthStore.getState() inside React components (only in non-React code)
  • Server state via React Query, NOT local state + useEffect for API data

Read the full file on GitHub · 143 lines

Changes

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.

  1. 9d ago First seen · 143 lines · 12 tokens per session scan A 88b31f3fc24a

Subscribe to this mod's changes

validate-conventions is a skill published in the GitHub repository FouadMagdy01/RNCopilot (42 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 1,208 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 2026-08-30.