How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
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.
lucky-aeonCLAUDE.mdlucky-aeon/AgentX/CLAUDE.md
ClassName.class); // Usage logger.info("User {} performed action {}", userId, action); logger.error("Failed to process request", exception); ``` ## Security Best Practices ### Authentication & Authorization - **JWT Tokens**: Use JWT for stateless authentication - **User Context**: Always
BradGrouxCLAUDE.mdBradGroux/veritas-kanban/CLAUDE.md
Copilot CLI, Hermes, and OpenClaw contracts are documented in `AGENTS.md` --- ## Lessons learned (Claude-specific) ### Security - ❌ Forgot global middleware — flagged missing per-route auth that was already in `app.use()`. Global middleware
23blocks-OSCLAUDE.md23blocks-OS/ai-maestro/CLAUDE.md
session.id` to that effect. - xterm: `convertEol: false`; load addons, then `open()`, then `fitAddon.fit()`. ## Security model No app-level authentication, by design: the server binds `0.0.0.0` for the local network
groqCLAUDE.mdgroq/openbench/CLAUDE.md
stability - Use the latest stable version as the minimum to keep dependencies healthy and secure - Check latest versions with `uv pip list --outdated` or on PyPI ## Key Commands ### Development Setup
ersinkocCLAUDE.mdersinkoc/tonl/CLAUDE.md
Feature integration**: End-to-end testing of complete workflows - **Performance benchmarks**: Comprehensive performance analysis - **Security testing**: 96 security-focused tests preventing vulnerabilities - **Example validation**: All documented examples are tested automatically
memex-labCLAUDE.mdmemex-lab/memex/CLAUDE.md
comment_agent/ │ ├── memory_agent/ │ ├── super_agent/ # Orchestrator │ ├── skills/ # Composable skills │ ├── built_in_tools/ │ ├── memory/ │ └── security/ ├── data/ │ ├── model/ # DTOs │ ├── repositories/ │ └── services/ ├── db/ # Drift database layer ├── domain/models/ # Domain models ├── l10n/ # ARB localization
rennf93CLAUDE.mdrennf93/fastapi-guard/CLAUDE.md
Claude Code) working in this repository. ## Project Overview FastAPI Guard is a production-ready security library for FastAPI applications that provides: - IP control and rate limiting - Request logging and monitoring
TrevorSCLAUDE.mdTrevorS/voxtral-mini-realtime-rs/CLAUDE.md
with subgroups). ## Web App `serve.mjs` — HTTPS dev server (self-signed cert for WebGPU secure context). Serves shards from `models/voxtral-q4-shards/` via `/api/shards` endpoint. `web/worker.js` — ES module WebWorker. Handles `init` (WASM + WebGPU
fredrikburmesterCLAUDE.mdfredrikburmester/streamystats/CLAUDE.md
hosted analytics platform for Jellyfin media servers. It provides watch statistics, AI-powered recommendations, security monitoring, and data visualization. Users deploy it via Docker alongside their Jellyfin instance. It continuously
terrysoCLAUDE.mdterryso/claude-auto-resume/CLAUDE.md
limits, waits for the restriction period to end, and then automatically continues the task. **⚠️ SECURITY NOTE**: This script uses `--dangerously-skip-permissions` flag, which bypasses all safety prompts and allows
H-mmerCLAUDE.mdH-mmer/pentest-agents/CLAUDE.md
particular, `tools/scaffold.py` no longer accepts `--type`; do not add examples that use it. ## Security Hygiene - Never hardcode platform usernames, email aliases, passwords, tokens, cookies, TOTP seeds, or target-specific account
dark-hxxCLAUDE.mddark-hxx/CLI-Manager/CLAUDE.md
imports, or execution flow.** Graph first; text search only for empty/`UNKNOWN`/literals. - For security review, `explain({target: "fileOrSymbol"})` lists taint findings (source→sink flows; needs `analyze --pdg`). ## Never
getmydiaCLAUDE.mdgetmydia/mydia/player/CLAUDE.md
Data Layer**: GraphQL documents with codegen, sent through each instance's `MydiaClient` - **Storage**: flutter_secure_storage (credentials), Hive (cache). Open Hive through `initAppHive()` in `core/storage/app_hive.dart`, never `Hive.initFlutter()` -- it puts boxes
IamshankhadeepCLAUDE.mdIamshankhadeep/ccseva/CLAUDE.md
services - **Renderer Process** (`src/`): React app handling UI and user interactions - **Preload Script** (`preload.ts`): Secure bridge exposing `electronAPI` to renderer ### Key Architectural Components #### Service Layer (Singleton Pattern) - **CCUsageService**: Spawns
ultimo-rsCLAUDE.mdultimo-rs/ultimo/CLAUDE.md
which phase their feature belongs to. - **Phases 1–7: shipped.** Core, WebSocket, sessions/testing, security & performance (JWT/API-key/OIDC auth, authz guards, security headers, CSRF, rate-limit, IP allow/deny, benchmark suite), static files
valkey-ioCLAUDE.mdvalkey-io/valkey-glide/CLAUDE.md
address all feedback: - performance analysis - code quality, style, best practices - test coverage - documentation clarity - security vulnerabilities and edge cases ## What the user cares about (all equally important): - Performance - low latency
regent-vcsCLAUDE.mdregent-vcs/re_gent/CLAUDE.md
separate processes. ### BLAKE3 for hashing Faster than SHA-256, parallelizable, modern security margin. Pure-Go implementation available (`lukechampine.com/blake3`). 256-bit output, hex-encoded. ### Object store and index responsibilities
zevndaCLAUDE.mdzevnda/steam-game-idler/CLAUDE.md
step. - **The Steam Web API key is only obfuscated (compile-time embedded), not actually secure** — a deliberate, permanent decision. The real fix (a project-controlled proxy server) is a real
ShokoAnimeCLAUDE.mdShokoAnime/ShokoServer/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
TechStarkCLAUDE.mdTechStark/opencv-js/CLAUDE.md
fallback config | | Test failures on `setupOpenCv()` | Async init not awaited | check test helper | ## Security - `dist/opencv.js` comes from our own CI build (OpenCV source + Emscripten) — verify origin before accepting external files
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
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 Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
