How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
juyterman1000CLAUDE.mdjuyterman1000/entroly/CLAUDE.md
/code) when working with code in this repository. ## Gstack Operating Protocol Use a gstack-style workflow for non-trivial Entroly work: **Think -> Plan -> Build -> Review -> Test -> Ship -> Reflect**. Entroly
yogsoth-aiCLAUDE.mdyogsoth-ai/de-anthropocentric-research-engine/ladder-foundry/CLAUDE.md
triple-CC pretrain generator (design doc: `D:\YOGSOTH-AI\context\2026-06-06-20-18-triple-cc-architecture.md`). Three nested Claude Code sessions act as a pseudo-NN training loop: ``` optimizer-cc (long-running orchestrator; = the driving
duolahyperchoCLAUDE.mdduolahypercho/fusion-fable/CLAUDE.md
here; it's how the user sees Claude's work. ONLY final deliverables (including code files). For simple single-file tasks (<100 lines), write directly here. Notes on user uploaded
aaronsbCLAUDE.mdaaronsb/obsidian-mcp-plugin/CLAUDE.md
this doc). Scorecard CI-gate idea: #165. ### Passing the source-code review — fix, never suppress The portal's **Source code** check *forbids disabling* a specific set of lint rules
MicrosoftCLAUDE.mdmicrosoft/conductor/docs/providers/claude.md
GATEWAY_TOKEN}`), never literal string values. Conductor embeds raw workflow source code inside the `yaml_source` attribute of `workflow_started` events. Hardcoding a literal secret key in YAML exposes
mudriiCLAUDE.mdmudrii/openclaw-dashboard/CLAUDE.md
make check, make all) ``` After writing code: ```sh go vet ./... # always run first — catches misuse before lint go fix ./... # applies modernizations in-place; review with git diff go test
nimrodfisherCLAUDE.mdnimrodfisher/data-analytics-skills/CLAUDE.md
CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## What this repo is A library of 31 reusable analytical skill definitions
MaxKmetCLAUDE.mdMaxKmet/idea-validation-agents/CLAUDE.md
App Idea Validation Agent — root configuration for Claude Code
Sidiora-LabsCLAUDE.mdSidiora-Labs/LayerX-Network/CLAUDE.md
cycles, 30-minute cap, and the stop condition. They report exit code and log path only. No duplicate reviews, no extra verification campaigns. - **Agreed Result**: Once verify_cmd passes, publish
cnfjlhjCLAUDE.mdcnfjlhj/ai-collab-playbook/CLAUDE.md
结论 → 展开”输出 - 涉及架构决策、多文件变更或不确定方案时，关键理由必须在输出中可见 - 敏感路径（安全 / 权限 / 隐私 / 支付 / 并发 / 性能）完成后追加 code review，优先使用 `self-review` ### 2.2 主动探索 - 宁可多探索 10 步，也不问本可自己找到答案的问题 - 探索顺序：代码搜索 / Read → 环境命令（Bash
secondskyCLAUDE.mdsecondsky/sap-skills/CLAUDE.md
Skills - Project Context **Repository**: https://github.com/secondsky/sap-skills **Purpose**: SAP development skills for AI coding assistants with evidence-tracked verification **Version**: 2.4.0 | **Plugins**: 40 | **Last Updated**: 2026-07-17 --- ## What This
edouard-claudeCLAUDE.mdedouard-claude/snip/CLAUDE.md
automatically 5. For first-time or local validation: `goreleaser release --snapshot --clean` ## Conventions - All code, comments, variable names, commits, and documentation files must be in English - Direct communication style
liangdabiaoCLAUDE.mdliangdabiao/claude-data-analysis/CLAUDE.md
Upload data → Run exploratory analysis → Review insights 2. **Visualization**: Analyze data → Generate visualizations → Export charts 3. **Reporting**: Complete analysis → Generate report → Share findings 4. **Code Generation**: Define requirements → Generate code
AncienttwoCLAUDE.mdAncienttwo/repo-harness/CLAUDE.md
sprint backlog or active plan `## Task Breakdown`; contract rows may expand into plan -> contract -> review -> notes only through the work-package gate. - If current repo state conflicts with the task
JetBrainsCLAUDE.mdJetBrains/youtrackdb/CLAUDE.md
details are in `.claude/docs/architecture.md`. ## Documentation Sync ### When to Update Documentation 1. **When modifying source code**: Review docs in `docs/` and module `README.md` files to see if any cover the area
cnighswongerCLAUDE.mdcnighswonger/claude-code-cache-fix/CLAUDE.md
opens PR, submits for review before implementing. - **Codex Review Agent** (external, OpenAI Codex) — independent code reviewer. Reviews on PRs, writes reports to `docs/code-reviews/` in the codex workspace. - **Proxy Test Agent
zhuzhaoyunCLAUDE.mdzhuzhaoyun/Molio/CLAUDE.md
改这条链路时要同时检查 `molio-connect/background.js`、`apps/desktop/src/main.js`、`apps/web/src/components/kb/KnowledgeBasePage.tsx` 和 `apps/web/src/hooks/useKnowledge.ts`。 ## Runtime Context Loading Agent CLI（Claude Code、Codex 等）通过 `cwd` 参数加载项目上下文。spawn 进程时设置 `cwd` 为项目的 `localPath`，agent CLI 会自动读取该目录下的 `CLAUDE.md`、`.claude
Gabson0xCLAUDE.mdGabson0x/bountyforge/skills/pashov/CLAUDE.md
focused, self-contained capability for Claude Code in VS Code and Cursor. ## Structure ``` solidity-auditor/ # Security review of Solidity changes while you develop CLAUDE.md # This file (read by Claude Code
alirezarezvaniCLAUDE.mdalirezarezvani/claude-code-aso-skill/CLAUDE.md
/lib/data_sources.md` - Installation: `.claude/INSTALL.md` - Usage: `.claude/USAGE.md` **Questions:** - Review agent definitions for detailed protocols - Check implementation plan for phase breakdowns - See data_sources.md for API limitations --- ## Coding Behaviour Guidelines These four principles (from
joshukraineCLAUDE.mdjoshukraine/dotfiles/CLAUDE.md
CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## About This Repository This is a personal dotfiles repository for macOS using
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.
