FlameskyDexiveCLAUDE.mdLegends-Of-Heroes
FlameskyDexive/Legends-Of-Heroes/CLAUDE.md
No summary in the file. Open it to read it.
CLAUDE.md examples from real projects
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Most stars first · from page 29Worked for most · soon
FlameskyDexiveCLAUDE.md
opentabs-devCLAUDE.mdopentabs / build-plugin
opentabs-dev/opentabs/.agents/skills/build-plugin/CLAUDE.md
SKILL.md is a lightweight stub with YAML frontmatter. AI clients cache it at session start. The stub instructs the AI to read SKILL.md on demand, ensuring the latest content is always used. Edit SKILL.md — the single source of truth. Changes take effect immediately. Only edit SKILL.md to change the name, description, or trigger keywords. This skill covers the full plugin lifecycle: building, icons, troubleshooting, setup, and writing learnings back. It consolidates content from the previously separate plugin-icon, troubleshoot, setup-plugin…
opentabs-devCLAUDE.mdopentabs / bump-version
opentabs-dev/opentabs/.agents/skills/bump-version/CLAUDE.md
AI clients load SKILL.md once at session start and cache its frontmatter + content in memory. To ensure the AI always gets the latest skill instructions (even if the skill was updated after the session started), SKILL.md is a lightweight stub that tells the AI to read SKILL.md at execution time. When you need to update the bump-version skill content: Update SKILL.md when: Some AI clients (e.g., Claude Code with the skill tool) load skill files into memory once at…
opentabs-devCLAUDE.mdopentabs / ralph
opentabs-dev/opentabs/.agents/skills/ralph/CLAUDE.md
AI clients load SKILL.md once at session start and cache its frontmatter + content in memory. To ensure the AI always gets the latest skill instructions (even if the skill was updated after the session started), SKILL.md is a lightweight stub that tells the AI to read SKILL.md at execution time. When you need to update the ralph skill content: Some AI clients (e.g., Claude Code with the skill tool) load skill files into memory once at the start of…
opentabs-devCLAUDE.mdopentabs
opentabs-dev/opentabs/docs/CLAUDE.md
The OpenTabs documentation site is built with Next.js 16, content-collections for MDX, and a neo-brutalist design system. Content is authored in MDX under content/, rendered via content-collections, and styled with Tailwind CSS 4. All checks must pass. This project has no test suite. npm run check runs them all sequentially, stopping on first failure. From the repo root, these convenience aliases are available: app/global.css defines the visual language as CSS custom properties. Key tokens: Shadows are flat offsets using var(--border)…
opentabs-devCLAUDE.mdopentabs / e2e
opentabs-dev/opentabs/e2e/CLAUDE.md
Playwright E2E tests that exercise the full stack: MCP server + Chrome extension + test web server + test plugin. Tests run under Playwright's Node.js test runner, so Node.js APIs are correct here. E2E tests spawn Chromium browsers, MCP server processes, and test servers. You MUST clean up processes you create without killing processes created by other agents running in parallel. Rules: E2E tests run under Playwright's Node.js test runner using Node.js APIs (node:fs, node:child_process, etc.). The MCP server test…
opentabs-devCLAUDE.mdopentabs / plugins
opentabs-dev/opentabs/plugins/CLAUDE.md
Plugins in plugins/ are fully standalone projects — exactly as if created by an external developer using npx @opentabs-dev/create-plugin. They are NOT part of the root npm workspace. Each plugin: The root tooling (npm run build, npm run lint, etc.) does NOT cover plugins. When changing platform packages that plugins depend on (shared, plugin-sdk, plugin-tools), publish new versions to npm and update plugin dependencies. *All plugins must use ^x.y.z semver ranges for @opentabs-dev/ dependencies — never file: or workspace: links.**…
MetaCLAUDE.mdProgramBench
facebookresearch/ProgramBench/CLAUDE.md
ProgramBench evaluates whether LM-based SWE-agents can reverse-engineer black-box software systems. The workflow: take an open-source CLI tool (mostly Rust/Go), compile it into a Docker image with source removed, then have an LM agent re-implement it from scratch by interacting only with the binary. Behavioral tests (also LM-generated) score the re-implementation. Some behavioral tests are unreliable and are excluded from scoring. Each excluded test is recorded under branches.<hash>.ignored_tests[] in a task's tests.json, with one or more reasons[].id explaining why. All ignored…
SethGammonCLAUDE.mdCitadel
SethGammon/Citadel/CLAUDE.md
An agent orchestration system for Claude Code. This repo IS the harness. The harness is a collection of skills, agents, hooks, and state files that enable Claude Code to operate autonomously on any codebase. It provides: - Intent routing (/do) that dispatches tasks to the right tool - Campaign persistence across sessions - Parallel agent coordination with discovery sharing - Automated quality enforcement through lifecycle hooks Always run tests after modifying hooks or skills. Five levels: Adding a new skill:…
MongoDBCLAUDE.mdmongo-php-driver
mongodb/mongo-php-driver/.claude/CLAUDE.md
This is the low-level MongoDB PHP extension (mongodb), written in C. It wraps libmongoc and libbson to expose a minimal PHP API for core driver functionality. Higher-level APIs live in the separate MongoDB PHP Library. Issues are tracked in the PHPC JIRA project. Commit messages and branch names reference JIRA ticket IDs (e.g., PHPC-2215). make test compiles the extension and loads it automatically — no need to run make all or make install first. For failed tests, all intermediate files…
bgauryyCLAUDE.mdoctocode
bgauryy/octocode/CLAUDE.md
Read AGENTS.md. Discover repository skills under .agents/skills and activate only those matching the task.
voicetreelabCLAUDE.mdvoicetree / backend
voicetreelab/voicetree/backend/claude.md
VoiceTree is a system which does online text stream to "abstraction graphs" conversion. An abstraction graph (or concept graph) is a collection of markdown notes, connected to each other via…
voicetreelabCLAUDE.mdvoicetree / webapp
voicetreelab/voicetree/webapp/claude.md
These instructions are for AI assistants working in this project. Always open @/openspec/AGENTS.md when the request: - Mentions planning or proposals (words like proposal, spec, change, plan) - Introduces new…
retentioneeringCLAUDE.mdretentioneering-tools
retentioneering/retentioneering-tools/CLAUDE.md
No summary in the file. Open it to read it.
awdr74100CLAUDE.mdfigwright
awdr74100/figwright/CLAUDE.md
Read AGENTS.md first — it's the single source of guidance for this repo: architecture, layout, tech stack, commands, conventions, release flow, and gotchas. Claude Code specifics:
thedaviddiasCLAUDE.mdllms-txt-hub
thedaviddias/llms-txt-hub/CLAUDE.md
When working with these technologies, read the corresponding skill for detailed reference: - Stripe: .agents/skills/stripe/SKILL.md - AI SDK: .agents/skills/ai-sdk/SKILL.md <!-- llmstxt:end -->
hAcKlycCLAUDE.mdMyAgents
hAcKlyc/MyAgents/CLAUDE.md
基于 Claude Agent SDK 的桌面端通用 Agent 产品。开源（AGPL-3.0-only）并提供单独商业授权；使用 Conventional Commits；不得提交密钥、令牌或用户隐私数据。 本文件只保留每类任务都值得占用注意力的项目心智模型、决策顺序和文档路由，不收录可由代码、lint、测试、package.json 或局部文档直接发现的完整规则表。 若文档与代码冲突，不要任选一个继续：先用实现、测试和 git 历史确认现状，再修正文档。不要因为一次局部事故就把新规则追加到本文件；只有“跨任务高频、无法就近推断、违反后代价高”的知识才应常驻。 Sidecar、Plugin Bridge、MCP Server 与 CLI 共用应用内置的单一 Node.js v24，不依赖用户系统安装的 Node。 Owner 和 source of truth 必须针对具体事实、scope 与…
reticlehqCLAUDE.mdreticle
reticlehq/reticle/CLAUDE.md
Master rules for this codebase. Read this first — the non-negotiables, layout, and conventions. Reticle is the proof layer for AI agents — it verifies a running web app from…
solatisCLAUDE.mdclaude-config / conventions
solatis/claude-config/conventions/CLAUDE.md
Universal conventions for agents and skills.
solatisCLAUDE.mdclaude-config
solatis/claude-config/.github/CLAUDE.md
GitHub configuration and CI/CD workflows.
About CLAUDE.md
What is CLAUDE.md?
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.