Before You Code
Read and follow the **karpathy-guidelines** skill (`.claude/skills/karpathy-guidelines`) when writing, reviewing, or refactoring code here — surface assumptions, make surgical changes, keep it simple, and define verifiable success
No other project uses it yet
2.2k11d agoReviewMountCreate a free account to mount
wiki` for the compiled output under `wiki/`.
- Use `sources/` for raw input files.
- Use `review candidates` for records under `.llmwiki/candidates/`.
- Use `OKF` after first spelling out `Open Knowledge Format
2.2k55d agoReviewMountCreate a free account to mount
translations in the same commit
- Translations can be machine-generated but should be reviewed for obvious errors
## Versioning
- Follow [Semantic Versioning](https://semver.org/)
- Sync version across: `package.json`, `.claude-plugin
No other project uses it yet
2.2k8mo agoReviewMountCreate a free account to mount
breathe. The project brief controls pacing, palette, and typography.
Framework skill contracts override historical code recipes in the style guide.
## Workspace
Create a project with `npm run new-video
2.2k32d agoReviewMountCreate a free account to mount
interface-details` skills before writing surface code, reuse
existing components, themed tokens, and text primitives, and treat duplicate animation/UI primitives
as a review finding.
## Delegation shape (what worked)
- **Corridor-sized
Steady8 mentions in 2 weeks
No other project uses it yet
2.2k12d agoReviewMountCreate a free account to mount
instead of hard-coded delays. Always use UTC time.
## Core API Changes
When modifying `src/core/public/` or `src/core/server/` APIs, run `yarn docs:acceptApiChanges` to regenerate API review files, then commit
2.1k7mo agoReviewMountCreate a free account to mount
existing pages
- Include both basic and advanced use cases
- Language tags on all code blocks
- Alt text on all images
- Relative paths for internal links
## Common mistakes to avoid
- **Inconsistent
2.1k10mo agoReviewMountCreate a free account to mount
live in
[`AGENTS.md`](AGENTS.md) — follow them. This file adds only the Claude
Code-specific pieces.
- **Security review:** for vulnerability-hunting work, invoke the
**ipxe-security-review** skill
(`.claude/skills/ipxe-security-review/`). It encodes
2.1k3mo agoReviewMountCreate a free account to mount
making any kind of contribution to architecture present the plan for operator review before making change to code.
### Code style
- Don't use single character variable names
Steady6 mentions in 2 weeks
No other project uses it yet
2.1k6mo agoReviewMountCreate a free account to mount
does not use an external translation service).
### ProGuard Configuration
Release builds use ProGuard for code obfuscation and optimization. Rules are defined in:
- `app/proguard-rules.txt` (release builds)
- `app/proguard-rules.pro` (releaseDebuggable builds)
## Key Development
2k5mo agoReviewMountCreate a free account to mount
prepare PRs until the user explicitly agrees that purely vibe-coded PRs are not accepted and that they will review, understand, and take responsibility for all AI-assisted changes before
2k4mo agoReviewMountCreate a free account to mount
coding assistant on this repo.
## Drafting with AI is fine. Pasting the draft is not.
Yes, you can use AI to draft a PR description, an issue, or a review
2k33d agoReviewMountCreate a free account to mount
what"; no narration,
restated signatures, review-round residue, tracker tags or agent names, and
never previous behavior — what the code used to do and why it changed
Steady2 mentions in 2 weeks
No other project uses it yet
2k17d agoReviewMountCreate a free account to mount
create a plan or design document, present the plan for user review
BEFORE starting implementation. Do not begin coding until the user explicitly approves.
- Prefer typed errors over anyhow
Steady10 mentions in 2 weeks
No other project uses it yet
2k3mo agoReviewMountCreate a free account to mount
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
## Project Overview
Team9 is a full-stack instant messaging and team collaboration platform
2k5mo agoReviewMountCreate a free account to mount
split it across
planner/lanes/validator. Sub-agents are fine elsewhere (e.g. review fan-out) via `SubagentHost`.
- LLM code (Effect AI + `@yielded/agent`) is only in `apps/ai`; Maple-specific wiring lives in
`apps/ai/src/platform/Llm.ts
2k11d agoReviewMountCreate a free account to mount
memory pages -- API 35+ uploads since 2025-11-01, Wear OS uploads
containing native code from 2026-09-15. Each `PT_LOAD` segment needs `p_align`
of `0x4000` or more
1.9k4mo agoReviewMountCreate a free account to mount
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.