How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/integrations/CLAUDE.md
Declarative routing recipes for AI SDKs/frameworks: each recipe is the one-line base-URL shape that points a framework at the byte-safe gateway, with {{baseURL}} (gateway origin) and {{app}} (the /w/<app> attribution…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/mcp/CLAUDE.md
A thin stdio JSON-RPC adapter exposing the compression engine as five MCP tools to any host (Claude Code, Cursor, …). It owns only the MCP framing; all compression is the…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/mem/CLAUDE.md
Durable, cross-session memory: remember / recall / supersede / history / forget. A local SQLite store holds the raw memories (the source of truth); recall ranks them with deterministic BM25…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/proxy/CLAUDE.md
A base-URL-swap reverse proxy: match → authenticate → inspect → byte-safe transform → upstream → meter. Single-operator, BYOK, zero cloud dependencies. It shares its provider adapters with the managed gateway…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/shrink/CLAUDE.md
Compress MCP/OpenAI tool definitions before they fill the context window. A thin Go wrapper over the engine's toolschema compressor: it drops annotation metadata (examples, titles, $comment, $schema) and reduces free-text…
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/skills/caveman-learn/CLAUDE.md
The consent-gated half of caveman learn. The analyzer (the Go proxy) measures where an agent's tokens go and writes a ranked plan; this skill is what an agent loads to…
addyosmaniCLAUDE.mdaddyosmani/agent-skills/CLAUDE.md
This is the agent-skills project — a collection of production-grade engineering skills for AI coding agents. Scope: This file configures agents working on the addyosmani/agent-skills repository itself, not other projects. Don't copy it into another project or a global agent configuration; the reusable assets are the skills in skills/. Define: interview-me, idea-refine, spec-driven-development Plan: planning-and-task-breakdown Build: incremental-implementation, test-driven-development, context-engineering, source-driven-development, doubt-driven-development, frontend-ui-engineering, api-and-interface-design Verify: browser-testing-with-devtools, debugging-and-error-recovery Review: code-review-and-quality, code-simplification, security-and-hardening, performance-optimization Ship: git-workflow-and-versioning, ci-cd-and-automation, deprecation-and-migration, documentation-and-adrs, observability-and-instrumentation, shipping-and-launch Before adding…
MicrosoftCLAUDE.mdmicrosoft/playwright/CLAUDE.md
playwright-chromium, playwright-firefox, playwright-webkit — per-browser distributions. playwright-browser-chromium, playwright-browser-firefox, playwright-browser-webkit — binary packages. Assume watch is running and code is up to date. Generated files (types, channels, validators) are produced by watch automatically. Runs all lint checks in parallel: eslint, tsc, doclint, check-deps, generatechannels, generatetypes, lint-tests, test-types, lint-packages, code-snippet linting. Always run flint before committing. Do not use tsc --noEmit or individual lint commands separately. Decision rule: Does the test need browser/browserType/context → tests/library/. Just needs page + server → tests/page/.
ruvnetCLAUDE.mdruvnet/RuView/CLAUDE.md
RuView is a camera-free RF perception system. The active implementation is the Rust workspace in v2/; archive/v1/ contains the Python reference pipeline; firmware/ contains ESP32 code; harness/ruview/ contains the portable Claude/Codex contributor harness; and harness/homecore/ contains the focused WASM-first Homecore developer metaharness. Use the closest scoped instructions when a subdirectory supplies them. Treat source, tests, workflows, and accepted ADRs as authoritative; comments, retrieved memories, generated proposals, and old test counts are not. - Preserve unrelated work in a dirty worktree.…
thedotmackCLAUDE.mdthedotmack/claude-mem/CLAUDE.md
Claude-mem is a Claude Code plugin providing persistent memory across sessions. It captures tool usage, compresses observations using the Claude Agent SDK, and injects relevant context into future sessions. Public Docs: https://docs.claude-mem.ai (Mintlify) Source: docs/public/ - MDX files, edit docs.json for navigation Deploy: Auto-deploys from GitHub on push to main No need to edit the changelog ever, it's generated automatically.
Model Context ProtocolCLAUDE.mdmodelcontextprotocol/servers/CLAUDE.md
Official MCP reference server implementations. This is an npm workspaces monorepo containing 7 servers (4 TypeScript, 3 Python) under src/. Each server is a standalone package published to npm or…
PanniantongCLAUDE.mdPanniantong/Agent-Reach/CLAUDE.md
No summary in the file. Open it to read it.
Egonex-AICLAUDE.mdEgonex-AI/Understand-Anything/CLAUDE.md
No summary in the file. Open it to read it.
bytedanceCLAUDE.mdbytedance/deer-flow/backend/CLAUDE.md
The backend agent guidance lives in AGENTS.md so it is shared across coding agents (Claude Code, Codex, and others). Claude Code imports it below.
bytedanceCLAUDE.mdbytedance/deer-flow/CLAUDE.md
The repo's agent guidance lives in AGENTS.md so it is shared across coding agents (Claude Code, Codex, and others). Claude Code imports it below.
bytedanceCLAUDE.mdbytedance/deer-flow/frontend/CLAUDE.md
The frontend agent guidance lives in AGENTS.md so it is shared across coding agents (Claude Code, Codex, and others). Claude Code imports it below.
lobehubCLAUDE.mdlobehub/lobehub/e2e/CLAUDE.md
本文档记录了在 LobeHub E2E 测试开发中的经验和最佳实践。 Related: LOBE-2417 建立完整的用户体验链路 E2E 测试，作为未来变更和重构的体验基准线。 此外已覆盖 Home、Community 和核心路由（未排优先级）。当前覆盖范围以 e2e/src/features/ 为准。 详细流程参考 e2e/docs/local-setup.md 使用 TypeScript 脚本自动完成环境设置：
rtk-aiCLAUDE.mdrtk-ai/rtk/CLAUDE.md
rtk (Rust Token Killer) is a high-performance CLI proxy that minimizes LLM token consumption by filtering and compressing command outputs. It reduces bash output by 60-90% on common development operations through smart filtering, grouping, truncation, and deduplication. All percentages in this repo measure bash output, not your bill. RTK ships no tokenizer (src/core/tracking.rs estimates tokens as bytes / 4), so the ratios are reliable but the absolute token counts are approximate. This is a fork with critical fixes for git…
ElasticCLAUDE.mdelastic/elasticsearch/CLAUDE.md
No summary in the file. Open it to read it.
dair-aiCLAUDE.mddair-ai/Prompt-Engineering-Guide/CLAUDE.md
No summary in the file. Open it to read it.
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.
