The MCP server source lives in microsoft/playwright, in packages/playwright-core/src/tools/. This repo ships @playwright/mcp: cli.js and index.js run the server from the playwright-core alpha that package.json pins. config.d.ts is a copy of the upstream file, and npm run lint generates the tool list in README.md. There is no build step. Tests are in tests/*.spec.ts, with test and expect from ./fixtures. The client fixture is an MCP client that runs cli.js over stdio, startClient() starts one with args or a config, and…
Steady8 mentions in 2 weeks
No other project uses it yet
39k13d agoReviewMountCreate a free account to mount
The CLI source lives in microsoft/playwright, in packages/playwright-core/src/tools/. This repo ships @playwright/cli: playwright-cli.js runs the CLI of the playwright-core alpha that package.json pins, and adds the update check, with skillCheck.js. skills/playwright-cli/ is a copy of the skill that playwright-cli install --skills writes, and node scripts/update.js refreshes it. There is no build step and no lint. Tests are in tests/integration.spec.ts. They run playwright-cli.js with runCli() in the output directory of the test, and the npmRegistry fixture serves a fake registry for…
15k7mo agoReviewMountCreate a free account to mount
To use the Claude API, create an account on the Anthropic Console and access your API key from the API keys section. Install the required Anthropic Python package: Configure the HOST_AGENT and APP_AGENT in the config/ufo/agents.yaml file to use the Claude API. If the file doesn't exist, copy it from the template: Edit config/ufo/agents.yaml with your Claude configuration: Configuration Fields: Available Models: For detailed configuration options, see: After configuration, you can start using UFO with the Claude API. Refer to…
No other project uses it yet
10k12mo agoReviewMountCreate a free account to mount
A plugin for Claude Code, Codex, the Copilot CLI and Pi (experimentally opencode, Cursor, Grok Build, Hermes Agent and the Antigravity CLI) that reads finished sessions and changes what later sessions in the same repository pay for: micro-skills, tool pruning, and a loop guard. See README.md for the overview and the method, docs/PLUGIN.md for the design and the verified agent behavior, and docs/ARCHITECTURE.md for how the package fits together.
POML (Prompt Orchestration Markup Language) is a structured markup language for advanced prompt engineering with LLMs. It provides an HTML-like syntax with semantic components, comprehensive data handling, and a CSS-like styling system. The project consists of: The core POML processor is built with TypeScript and React:
5k15mo agoReviewMountCreate a free account to mount
This file provides guidance to Claude Code when working with the POML browser extension package. The POML Browser Extension (packages/poml-browser/) provides POML support in web browsers through a Chrome extension. It enables users to extract content from web pages, manage it as cards, and convert it to POML format. Important notes on building and testing for Claude: As developers usually run a long-running watch process, please do not emit build commands by yourself. Do not run tests on your own.…
5k15mo agoReviewMountCreate a free account to mount
GitRest provides a REST API to Git repositories, modeled after GitHub's REST APIs. It is part of the Fluid Framework server infrastructure. Endpoints follow the GitHub API pattern:
4.9k3mo agoReviewMountCreate a free account to mount
Historian is a service that tracks the historical record for a Fluid document. It acts as a proxy to the underlying git repository that maintains versioned snapshots. This is a release group root with two packages: Runtime config is in packages/historian/config.json and loaded via nconf.
4.9k3mo agoReviewMountCreate a free account to mount
Read AGENTS.md in this repository first. It contains all project-specific knowledge (build workflow, pass architecture, syntax, conventions, etc.). Everything below is Claude-specific for this project. (Add Claude-specific project instructions here as needed.)
3.7k3mo agoReviewMountCreate a free account to mount
Power Fx is a low-code general-purpose programming language based on spreadsheet-like formulas. This is the open-source C# implementation used across Microsoft Power Platform. The codebase contains a complete compiler and interpreter. Build configurations: Debug/Release (single-target), Debug462/Release462 (net462 only), Debug70/Release70 (net7.0 only), DebugAll/ReleaseAll (multi-target, used by local build scripts). Separation of Compilation and Execution: Core compiles to IR with zero evaluation code. Multiple backends (JavaScript, SQL, etc.) can consume the same IR independently. Symbol Table Composition: Layered symbol tables (Config ->…
3.4k6mo agoReviewMountCreate a free account to mount
Power Fx is a low-code general-purpose programming language based on spreadsheet-like formulas. This is the open-source implementation of the language used across Microsoft Power Platform. The codebase contains a complete compiler and interpreter infrastructure written in C#. Note: The runLocalTests.cmd script runs tests for both .NET Framework 4.6.2 and .NET 7.0 configurations using VSTest. The Power Fx implementation follows a classic multi-phase compiler architecture: Expression Text → [Lexer] → Tokens → [Parser] → AST → [Binder] → Typed AST →…
3.4k6mo agoReviewMountCreate a free account to mount
Follow .github/workflows/tests.yml for the canonical sequence. Tests take ~8 minutes. Always save output to a file and grep from there: The tests are NUnit tests in src/Playwright.Tests/, one class per upstream spec file: PageRouteTests.cs ports tests/page/page-route.spec.ts. Locator and assertion classes are in Locator/ and Assertions/. A regression test is one added case in the class that owns the feature, also when only the port has the bug.
Steady2 mentions in 2 weeks
No other project uses it yet
3k25d agoReviewMountCreate a free account to mount
Clarity is an open-source TypeScript behavioral analytics library for tracking user interactions and session replays. Monorepo with Lerna/Yarn workspaces: Stack: TypeScript, Rollup, TSLint, Playwright, Lerna, Yarn workspaces Critical: clarity-js has two top priorities that must guide all development decisions: Rollup + TypeScript → multiple formats (CJS, ESM, IIFE minified). Build artifacts auto-cleaned to build/ or extension/ (gitignored). Build outputs per package: - clarity-js: clarity.js (CJS), clarity.module.js (ESM), clarity.min.js (minified), plus variants: clarity.extended.js, clarity.insight.js, clarity.performance.js, clarity.livechat.js, and dynamic module builds (clarity.tidio.js,…
2.8k8mo agoReviewMountCreate a free account to mount
The repository coding and comment rules live in AGENTS.md. Read that file first. Rules scoped to a path, including the contract for the files under Examples/, live in .github/instructions/. IMPORTANT: This project has a knowledge graph. ALWAYS use the code-review-graph MCP tools BEFORE using Grep/Glob/Read to explore the codebase. The graph is faster, cheaper (fewer tokens), and gives you structural context (callers, dependents, test coverage) that file scanning cannot. Fall back to Grep/Glob/Read only when the graph doesn't cover what…
2.5k3mo agoReviewMountCreate a free account to mount
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.
MicrosoftCLAUDE.md