How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
peterkrueckCLAUDE.mdpeterkrueck/Claude-Code-Development-Kit/templates/CLAUDE.md
complexity, stop and reassess rather than pushing through. - **Use available skills proactively**: `/review-work` for code review, `/update-docs` after significant changes, `/deploy` for deployments. - **Context7 first**: When working with external libraries
elirantutiaCLAUDE.mdelirantutia/vibeyard/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
OpenRaiserCLAUDE.mdOpenRaiser/NanoResearch/CLAUDE.md
Pipeline NanoResearch uses a 9-stage pipeline: ```text IDEATION -> PLANNING -> SETUP -> CODING -> EXECUTION -> ANALYSIS -> FIGURE_GEN -> WRITING -> REVIEW ``` Stage meanings: - `ideation`: literature search, gap finding, hypothesis or theme extraction - `planning
Team-CommonlyCLAUDE.mdTeam-Commonly/commonly/CLAUDE.md
ACCOUNT`) or via ExternalSecrets. - **UI verification**: Use MCP Playwright (`mcp__playwright__*`) ### 📁 Key Documentation Files - **Code Review Rubric**: `/REVIEW.md` — **REQUIRED READING** before any code review, implementation planning, or pre-commit self
jayminwestCLAUDE.mdjayminwest/overstory/CLAUDE.md
configurable (default 2). Prevents runaway spawning. ### Runtime Modes: headless vs tmux (Claude Code) Claude Code agents can run in two modes. **Headless is the shipped default for new projects
sceneviewCLAUDE.mdsceneview/sceneview/CLAUDE.md
every API, doc and sample: can an AI read this and emit working code on the first try? If not, simplify the API or fix the doc until
sipyourdrink-ltdCLAUDE.mdsipyourdrink-ltd/bernstein/CLAUDE.md
offline, from the artifacts alone. CLI coding agents work out of the box (Claude Code, Codex, Gemini CLI, and 52 more), and the same layer governs any agent workload
dohoooCLAUDE.mddohooo/helmor/CLAUDE.md
lines to improve re-render isolation. All files < 300 lines. | | `components/ai/` | AI-specific components (code block, file tree, reasoning). | | `components/ui/` | shadcn/ui primitives (base-nova). | | `lib/api.ts` | IPC bridge -- every Tauri `invoke
piominCLAUDE.mdpiomin/claude-ai-spring-boot/CLAUDE.md
prevent the same mistake - Ruthlessly iterate on these lessons until the mistake rate drops - Review lessons at session start for a project ### 3. Verification Before Done - Never mark a task
d-kimusonCLAUDE.mdd-kimuson/claude-code-viewer/CLAUDE.md
general-purpose subagent with this file path | | `docs/guidelines/internal_review.md` | When requesting a code review
kbwoCLAUDE.mdkbwo/ccmanager/CLAUDE.md
style and typing before review. - `bun run test` runs the Vitest suite once; combine with `bun run prepublishOnly` before publishing to exercise the full pipeline. ## Coding Style & Naming Conventions - Follow
SupabaseCLAUDE.mdsupabase/postgres-meta/CLAUDE.md
position marker - Position calculation accounts for injected `SET statement_timeout` prefix - Returns structured errors: `{ code, message, formattedError, position, detail, hint }` ### Type Generation Type generation (`npm run gen:types:*`) works
modu-aiCLAUDE.mdmodu-ai/moai-adk/CLAUDE.md
analyze dependencies before parallel execution, report progress per unit. - **Rule 3 — Post-Implementation Review**: After coding, provide potential-issue list (edge cases, error/concurrency scenarios), suggested test cases, known limitations/assumptions, additional
huytieuCLAUDE.mdhuytieu/COG-second-brain/CLAUDE.md
file per run**. Multi-file outputs (staging files, per-worker dumps, split reports) make review impossible. - **Default: work in a single file.** If the task fits in one file, never
fivetakuCLAUDE.mdfivetaku/gptaku_plugins/CLAUDE.md
docs-guide/ gaseo/ # Paseo 세션 등록 git-teacher/ goaljaby/ insane-design/ insane-research/ insane-review/ # GPT Pro 웹 브릿지 코드 리뷰 insane-search/ kkirikkiri/ nopal/ pumasi/ sangse/ # 상세페이지 컷 시트
fcakyonCLAUDE.mdfcakyon/claude-codex-settings/.claude/CLAUDE.md
files, and check related code for consistency. Never create docs (*.md, README) unless asked. - Prefer `rg` over `grep`. - Use the `writing-guidelines` skill to review documentation or interface copy
vm0-aiCLAUDE.mdvm0-ai/vm0/CLAUDE.md
lint/type suppression comments. Use static production imports and fix violations at their source. See [code quality](docs/bad-smell.md) for the project's specific boundaries. - Write repository artifacts, comments, commits, issues
RchGravCLAUDE.mdRchGrav/claudebox/claude/CLAUDE.md
command for complete legacy code workflow, assessment guidance, and commit sequence examples. ### Post-Implementation Code Review and Refactoring **After all tests pass, always consider refactoring opportunities in new code
RchGravCLAUDE.mdRchGrav/claudebox/CLAUDE.md
Think of yourself as a careful craftsperson who measures twice and cuts once. When reviewing code, always state: "I've read through [specific sections] and understand [key functionality]" before making
yuanchengluCLAUDE.mdyuanchenglu/claude-code-webui/CLAUDE.md
components 6. **Project Directory Selection**: User-chosen working directories for contextual file access ## Claude Code SDK Types Reference **SDK Types**: `frontend/node_modules/@anthropic-ai/claude-code/sdk.d.ts` ```typescript // Type extraction const systemMsg = sdkMessage
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.
