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.
ruvnetCLAUDE.mdruvnet/ruflo/v3/CLAUDE.md
This directory contains the V3 monorepo packages. Root CLAUDE.md rules apply here. Source of truth: docs/reviews/intelligence-system-audit-2026-05-29.md + scripts/benchmark-intelligence.mjs. Numbers below are measured unless marked "target/unverified".
Steady55 mentions in 2 weeks
2 projects use a version of this
ruvnetCLAUDE.mdruvnet/metaharness/kimi-k3-harness/CLAUDE.md
Repo-aware coding agent harness for kimi-k3-in-c — Kimi K3 (2.78T-param) inference in portable C99: one CPU, 8 GB RAM, no BLAS, no framework, no GPU Advanced Coding harness · domain: software-engineering. Generated with create-agent-harness. This harness uses @metaharness/kernel — a Rust-compiled WASM module with a NAPI-RS native fallback — so the same code runs identically on every platform. This harness targets kimi-k3-in-c — Kimi K3 (2.78 T parameters) inference in portable C99. One CPU, 8 GB of RAM. No BLAS,…
ruvnetCLAUDE.mdruvnet/ruvnet/claude.md
The SPARC Automated Development System (claude-sparc.sh) is a comprehensive, agentic workflow for automated software development using the SPARC methodology (Specification, Pseudocode, Architecture, Refinement, Completion). This system leverages Claude Code's built-in…
ruvnetCLAUDE.mdruvnet/QuDAG/CLAUDE.md
No summary in the file. Open it to read it.
ruvnetCLAUDE.mdruvnet/midstream/CLAUDE.md
ABSOLUTE RULES: 1. ALL operations MUST be concurrent/parallel in a single message 2. NEVER save working files, text/mds and tests to the root folder 3. ALWAYS organize files in appropriate subdirectories 4. USE CLAUDE CODE'S TASK TOOL for spawning agents concurrently, not just MCP MANDATORY PATTERNS: - TodoWrite: ALWAYS batch ALL todos in ONE call (5-10+ todos minimum) - Task tool (Claude Code): ALWAYS spawn ALL agents in ONE message with full instructions - File operations: ALWAYS batch ALL reads/writes/edits…
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.
