Noyara
AGENTS.md1 starsChanged 3 months agoMITView on GitHub
Read the exact versioned docs at https://docs.expo.dev/versions/v57.0.0/ before writing any Expo code. Use the matching official Expo skill before changing routing, native UI, upgrades, hosting, or store configuration. Don't assume. Don't hide confusion. Surface tradeoffs. LLMs often pick an interpretation silently and run with it. This principle forces explicit reasoning: Minimum code that solves the problem. Nothing speculative. Combat the tendency toward overengineering: The test: Would a senior engineer say this is overcomplicated? If yes, simplify. Touch only what you…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository9 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- eas-hostingSkill
- expo-native-uiSkill
- expo-routerSkill
- expo-uiSkill
- expo-upgradeSkill
- humanizerSkill
- noyara-merge-readySkill
- papercutsSkill
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
27 rules. About 0 are common, 23 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈23
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Read the exact versioned docs at https://docs.expo.dev/versions/v57.0.0/ before writing any Expo code.
- Distinctive: line 6
Use the matching official Expo skill before changing routing, native UI, upgrades, hosting, or store configuration.
- Distinctive: line 25
No features beyond what was asked
- Distinctive: line 26
No abstractions for single-use code
- Distinctive: line 28
No error handling for impossible scenarios
- Distinctive: line 29
If 200 lines could be 50, rewrite it
- Distinctive: line 37
When editing existing code:
- Distinctive: line 39
Don't "improve" adjacent code, comments, or formatting
- Distinctive: line 40
Don't refactor things that aren't broken
- Distinctive: line 42
If you notice unrelated dead code, mention it — don't delete it
- Distinctive: line 44
When your changes create orphans:
- Very specific: line 46
Remove imports/variables/functions that YOUR changes made unused
- Distinctive: line 47
Don't remove pre-existing dead code unless asked
- Distinctive: line 49
The test: Every changed line should trace directly to the user's request.
- Distinctive: line 75
Prefer simple, readable, flat code with minimal indirection.
- Distinctive: line 76
Search for existing implementations and installed libraries before creating new helpers or abstractions.
- Distinctive: line 79
Use Expo Router APIs for routing and navigation.
- Distinctive: line 80
Prefer universal React Native code.
- Very specific: line 81
Use @expo/ui when native SwiftUI or Jetpack Compose controls provide a concrete benefit.
- Very specific: line 82
Keep secrets out of the client bundle.
- Distinctive: line 83
Use idiomatic TypeScript and validate untrusted data at trust boundaries.
- Distinctive: line 84
Prefer established project helpers and libraries over hand-rolled implementations.
- Distinctive: line 85
Verify user-visible changes on every affected platform available locally and report any platform not tested.
- Distinctive: line 91
Do not mine an entire session for papercuts or start a broad cleanup unless the user explicitly asks.
- Distinctive: line 95
Use an i18n architecture from the start: no user-facing strings in business logic, and locale-aware formatting at presentation boundaries.
- Distinctive: line 96
Use BCP 47 locale identifiers and locale-aware presentation formatting.
- Very specific: line 98
Use Semantic Versioning and Conventional Commits.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
Agent guidance
Expo has changed
Read the exact versioned docs at https://docs.expo.dev/versions/v57.0.0/ before writing any Expo code. Use the matching official Expo skill before changing routing, native UI, upgrades, hosting, or store configuration.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
LLMs often pick an interpretation silently and run with it. This principle forces explicit reasoning:
- State assumptions explicitly — If uncertain, ask rather than guess
- Present multiple interpretations — Don't pick silently when ambiguity exists
- Push back when warranted — If a simpler approach exists, say so
- Stop when confused — Name what's unclear and ask for clarification
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
Combat the tendency toward overengineering:
- No features beyond what was asked
- No abstractions for single-use code
- No "flexibility" or "configurability" that wasn't requested
- No error handling for impossible scenarios
- If 200 lines could be 50, rewrite it
The test: Would a senior engineer say this is overcomplicated? If yes, simplify.
3. Surgical Changes
Touch only what you must. Clean up only your own mess.
When editing existing code:
- Don't "improve" adjacent code, comments, or formatting
- Don't refactor things that aren't broken
- Match existing style, even if you'd do it differently
- If you notice unrelated dead code, mention it — don't delete it
When your changes create orphans:
- Remove imports/variables/functions that YOUR changes made unused
- Don't remove pre-existing dead code unless asked
The test: Every changed line should trace directly to the user's request.
4. Goal-Driven Execution
Define success criteria. Loop until verified.
Transform imperative tasks into verifiable goals:
| Instead of... | Transform to... |
| "Add validation" | "Write tests for invalid inputs, then make them pass" |
| "Fix the bug" | "Write a test that reproduces it, then make it pass" |
| "Refactor X" | "Ensure tests pass before and after" |
For multi-step tasks, state a brief plan:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]Strong success criteria let the LLM loop independently. Weak criteria ("make it work") require constant clarification.
Engineering principles
- Prefer simple, readable, flat code with minimal indirection.
- Search for existing implementations and installed libraries before creating new helpers or abstractions.
- Abstract when it prevents meaningful drift and makes the result simpler to maintain. Avoid speculative or one-use abstraction layers.
- Install Expo-compatible dependencies with
npx expo install. - Use Expo Router APIs for routing and navigation. Do not import React Navigation packages directly in application code.
- Prefer universal React Native code. Add platform-specific files only for genuine platform differences.
- Use
@expo/uiwhen native SwiftUI or Jetpack Compose controls provide a concrete benefit. - Keep secrets out of the client bundle. Values prefixed with
EXPO_PUBLIC_are public. - Use idiomatic TypeScript and validate untrusted data at trust boundaries.
- Prefer established project helpers and libraries over hand-rolled implementations.
- Verify user-visible changes on every affected platform available locally and report any platform not tested.
Log papercuts
When small, non-blocking repository friction occurs — confusing setup, a reproducibly flaky repository command, stale generated files, a misleading in-repo error, or a non-obvious gotcha — use the papercuts skill and append it to .agents/PAPERCUTS.md in the moment. Continue the current task. Environment failures, transient flakiness, real bugs, and sensitive data are not papercuts.
Do not mine an entire session for papercuts or start a broad cleanup unless the user explicitly asks.
Architecture and data standards
- Use an i18n architecture from the start: no user-facing strings in business logic, and locale-aware formatting at presentation boundaries.
- Use BCP 47 locale identifiers and locale-aware presentation formatting.
- Accessibility: WCAG 2.2 AA. Mobile security: OWASP MASVS as applicable.
- Use Semantic Versioning and Conventional Commits. Use
camelCasefor variables/functions,PascalCasefor components/types, and kebab-case for URL paths.
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.

