expo_boilerplate
CLAUDE.md34 starsChanged 5 months agoMITView on GitHub
Context file for Claude Code. This acts as an entrypoint routing to our decoupled rule files. ⛔ This repo's trunk is development. It is the GitHub default branch and the base for every PR. ⛔ main does not exist here. gh api repos/chohra-med/expo_boilerplate/branches/main returns 404. Do not create it, do not target it, and do not assume it from habit. A PR opened against main cannot be merged because there is nothing to merge into. ⚠️ The estate is split…
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/app_feature_first_architecture.mdcCursor rule
- .cursor/rules/app_rules.mdcCursor rule
- .cursor/rules/best_practices.mdcCursor rule
- mobilelauncherSkill
- spec-harness-auditSkill
- spec-harness-buildSkill
- spec-harness-generate-agentsSkill
- spec-harness-installSkill
- spec-harness-learnSkill
- spec-harness-planSkill
- spec-harness-rulesSkill
- spec-harnessSkill
- spec-harness-specSkill
- spec-harness-tasksSkill
- spec-harness-ticketsSkill
- spec-harness-verifySkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 58
Before performing complex tasks, reading or creating files, you MUST review the relevant rule files:
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CLAUDE.md — MobileLauncher LT
Context file for Claude Code. This acts as an entrypoint routing to our decoupled rule files.
🌿 Branches — the trunk is development, there is NO main
⛔ This repo's trunk is development. It is the GitHub default branch and the base for every PR.
⛔ main does not exist here. gh api repos/chohra-med/expo_boilerplate/branches/main returns 404. Do not
create it, do not target it, and do not assume it from habit. A PR opened against main cannot be
merged because there is nothing to merge into.
⚠️ The estate is split by family — this is where the confusion comes from:
| Family | Trunk |
| The AI Mobile Launcher variants (Standard · AI · openSource), Morrow Self, Mane | development |
The getwireai repos (getwireai_website, wireai-onboarding-server, wireai-activation) | main |
So "merge to main" is correct advice for the getwireai repos and wrong for this one. Read the default branch rather than carrying a habit across families:
gh repo view --json defaultBranchRef -q .defaultBranchRef.name⛔ A merge to development here is NOT a release. This is a React Native / Expo app: shipping to
users requires a new native build, not a merge. Never report a merged PR as shipped.
⛔ A checkout is not its trunk. Local development drifts behind origin/development routinely.
Base branches on origin/development and read trunk content with
git show origin/development:<path>, never from the working tree.
Project skill
This repo ships a Claude Code skill for code generation. To use it: /mobilelauncher <command>
Available commands: orient · feature <name> · screen <feature> <name> · component <name> · hook <name> · slice <feature> · endpoint <feature> <name> · schema <name>
See CLAUDE_SKILL.md for full documentation. Skill file: .claude/skills/mobilelauncher/skill.md
What this project is
AI-first React Native + Expo boilerplate. Feature-first architecture designed to produce consistent, predictable code with AI coding tools. Lite version of AI Mobile Launcher.
Stack: Expo 55 · React Native 0.83.6 · React 19 · TypeScript strict · Redux Toolkit + RTK Query · Restyle · MMKV · Reanimated 4 · FlashList · Biome · i18next · Zod
The Master Rules
CRITICAL: To prevent drift and redundancy, all AI development rules reside in the .cursor/rules/ directory.
Before performing complex tasks, reading or creating files, you MUST review the relevant rule files:
| Topic | Look in |
| Full Architecture & Feature-First Directory Structure | .cursor/rules/app_feature_first_architecture.mdc |
| Code Standards, UI, Navigation, Redux, State & Testing | .cursor/rules/app_rules.mdc |
| Advanced Best Practices (Error Handling, Env Vars, A11y) | .cursor/rules/best_practices.mdc |
| Base Architecture Explanations | ai_articles/memory-bank/ |
Please proactively read these files as necessary to maintain consistency.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.