CLAUDE.md examples from real projects

AnthropicCLAUDE.md

claude-code

anthropics/claude-code/CLAUDE.md

that the allowed tools do not cover then runs only if Claude Code's safety review passes it. Allow only the tools the job needs, and keep any `--disallowedTools` list

nextlevelbuilderCLAUDE.md

ui-ux-pro-max-skill / stack

nextlevelbuilder/ui-ux-pro-max-skill/stack/CLAUDE.md

primitives. 4. **SEE IT — Playwright / Chrome DevTools MCP.** You are not done when the code compiles. Open the page in a real browser, screenshot it, read the console, exercise interactive

garrytanReads credentialsCLAUDE.md

gstack

garrytan/gstack/CLAUDE.md

required selected evaluations, then run the full free suite once on the final integrated code. During repairs, focused checks replace a full-suite run before every commit. `bun run test

electronCLAUDE.md

electron

electron/electron/CLAUDE.md

label list --repo electron/electron --search target/ --json name,color --jq '.[] | select(.color == "ad244f") | .name' ``` ## Code Style **C++:** Follows Chromium style, enforced by clang-format **TypeScript/JavaScript:** [oxlint](https://oxc.rs/docs/guide/usage/linter) configuration

No other project uses it yet

JuliusBrusseePipes a download into a shellCLAUDE.md

caveman

JuliusBrussee/caveman/CLAUDE.md

installer/install.js` and `src/tools/caveman-init.js`. | | `skills/caveman-commit/SKILL.md` | Caveman commit message behavior. Fully independent skill. | | `skills/caveman-review/SKILL.md` | Caveman code review behavior. Fully independent skill. | | `skills/caveman-help/SKILL.md` | Quick-reference card. One-shot display, not a persistent mode

addyosmaniCLAUDE.md

agent-skills

addyosmani/agent-skills/CLAUDE.md

skills/`. ## Project Structure ``` skills/ → Core skills (SKILL.md per directory) agents/ → Reusable agent personas (code-reviewer, test-engineer, security-auditor, web-performance-auditor) hooks/ → Session lifecycle hooks .claude/commands/ → Slash commands (/spec

denolandCLAUDE.md

deno

denoland/deno/CLAUDE.md

into `main` via pull requests. When the feature is finished and ready to for review, follow these steps: - Create a new git branch, if you haven't already, with

No other project uses it yet

pytorchCLAUDE.md

pytorch

pytorch/pytorch/CLAUDE.md

manages those. - **Finding the PR.** If the user asks to pull CI results or code review for a ghstack commit, get the PR URL from the `Pull-Request` trailer

No other project uses it yet

ruvnetReads credentialsCLAUDE.md

wifi-densepose

ruvnet/wifi-densepose/CLAUDE.md

wasm node harness/homecore/bin/cli.js verify --repo . --profile wasm node harness/homecore/bin/cli.js agent run \ --host claude-code --repo . --prompt "Review the plugin trust boundary" node harness/homecore/bin/cli.js mcp start ``` The package requests the metaharness

pbakausReads credentialsCLAUDE.md

impeccable

pbakaus/impeccable/CLAUDE.md

test`. New cases are recorded from the binary (`record.mjs --bin`) and reviewed by hand. `tests/oracle/vectors/calls/` is the frozen function-level snapshot; it cannot be regenerated. - **What stays JavaScript here

debpalashCLAUDE.md

VoiceStudio

debpalash/VoiceStudio/CLAUDE.md

networks, the Supertonic-3 engine, in-repo Markdown docs). Follow the patterns in the code itself; the durable *don'ts* that research established: - **No third-party endpoints for bug reporting

oven-shCLAUDE.md

bun

oven-sh/bun/CLAUDE.md

builtins/` - Core JavaScript builtins (streams, console, etc.) ## Landing PRs: What Bun Reviewers Catch The code review rules — what blocks merges, distilled from ~2,500 merged PRs — live in `REVIEW.md`. Read

oven-shCLAUDE.md

bun / workflows

oven-sh/bun/.github/workflows/CLAUDE.md

Rust toolchain: 1. Bump `channel` in `rust-toolchain.toml`. 2. Bump `RUSTUP_TOOLCHAIN` in the `Format Code` step's `env:` block in `format.yml` to the same value. 3. Bump `RUSTUP_TOOLCHAIN

Lum1104Deletes or force-pushesCLAUDE.md

Understand-Anything

Lum1104/Understand-Anything/CLAUDE.md

Architecture - **Monorepo** with pnpm workspaces - **understand-anything-plugin/** — Claude Code plugin containing all source code: - **packages/core** — Shared analysis engine (types, persistence, tree-sitter, search, schema, tours, plugins) - **packages/dashboard** — React + TypeScript

ruvnetReads credentialsCLAUDE.md

claude-flow

ruvnet/claude-flow/CLAUDE.md

platforms cross-validating | | Limited reasoning styles | Complementary strengths | | No external verification | Built-in code review | | Sequential workflows | Parallel execution | ### Dual-Mode Swarm Protocol For complex tasks, spawn both Claude

ruvnetReads credentialsCLAUDE.md

ruflo

ruvnet/ruflo/CLAUDE.md

platforms cross-validating | | Limited reasoning styles | Complementary strengths | | No external verification | Built-in code review | | Sequential workflows | Parallel execution | ### Dual-Mode Swarm Protocol For complex tasks, spawn both Claude

No other project uses it yet

MadsLorentzenCLAUDE.md

ai-job-search

MadsLorentzen/ai-job-search/CLAUDE.md

Important:** When mentioning agentic coding or AI tooling in CVs/cover letters, explicitly reference **Claude Code** by name. ## Verification Checklist After creating or updating a CV or cover letter, re-read

shanraisshanCLAUDE.md

claude-code-best-practice

shanraisshan/claude-code-best-practice/CLAUDE.md

individual hooks in `hooks-config.json`. ## Answering Best Practice Questions When the user asks a Claude Code best practice question, **always search this repo first** (`best-practice/`, `reports/`, `tips/`, `implementation/`, and `README.md

No other project uses it yet

leonardomsoCLAUDE.md

33-js-concepts

leonardomso/33-js-concepts/.claude/CLAUDE.md

page Phase 3: test-writer → Generate tests for code examples Phase 4: fact-check → Verify technical accuracy Phase 5: seo-review → Optimize for search visibility ``` **When to invoke:** - Creating

No other project uses it yet

vectorize-ioReads credentialsCLAUDE.md

hindsight

vectorize-io/hindsight/CLAUDE.md

must fix" issues before considering the task done. **MANDATORY: Run `/code-review` before pushing code or creating a pull request.** Do not push or create a PR until all "must