Auto-loaded when Claude Code works within web/e2e/. Covers what belongs in this directory, how to write specs that survive any sandbox, and the boundary between tracked core specs and untracked ad-hoc specs. For frontend patterns see web/CLAUDE.md. Playwright drives the deployed application, so it is the only layer that proves a frontend change reached users. Jest proves a component behaves; Playwright proves the built, published bundle behaves. :::danger[A source-only fix proves nothing here] These specs run against E2E_BASE_URL, which is…
14641d agoReviewMountCreate a free account to mount
Auto-loaded when working within web/src/visualizerPlugin/. See web/CLAUDE.md for the frontend-wide steering. The 3D/media viewer system uses a plugin-based architecture: Viewer plugins live under viewers/{Name}ViewerPlugin/ — each plugin ID below maps to a directory of that form (e.g. potree-viewer → viewers/PotreeViewerPlugin/). Per-viewer custom-install scripts live in web/customInstalls/ (one dir per viewer, plus a shared utility/ helper dir) and are executed by the postinstall chain in web/package.json.
14641d agoReviewMountCreate a free account to mount
This repository consolidates open-source tools for AWS DevOps Agent — skills, custom agents, and MCP servers, plus supporting infrastructure templates. Follow these conventions when contributing. See CONTRIBUTING.md for the full contribution workflow. This repository holds DevOps Agent tools only: skills, custom agents, and lightweight MCP servers that support them. It isn't a home for broader solutions.
13711d agoReviewMountCreate a free account to mount
This is a monorepo containing two related security-focused npm packages for hardening markdown against data exfiltration attacks through LLM prompt injection: Both packages use pnpm (not npm) as the package manager. Both packages share the tests based on markdown-to-markdown-sanitizer/tests/bypass-attempts/\*.md. Adding more examples hardens both packages Both packages are designed for defensive security use only:
13115mo agoReviewMountCreate a free account to mount
This is a robust markdown sanitizer that filters URLs in markdown links and images against prefix allow-lists, with comprehensive HTML sanitization. The sanitizer uses a sophisticated markdown-to-HTML-to-markdown pipeline to ensure security while preserving markdown structure. The sanitizer follows this flow: Always use pnpm, not npm. The codebase includes extensive security testing with 111 bypass attempt files that test various attack vectors: Tests use Vitest and run against multiple markdown parsers (remark, marked, markdown-it, showdown, commonmark) to ensure comprehensive coverage. The…
13115mo agoReviewMountCreate a free account to mount
This is a content/plugin repository, not an application. It ships an AI-agent evaluation toolkit for Copilot Studio in two parallel forms: There is no build, no test runner, no lint step. Changes are validated by running the skills end-to-end against an agent description. AGENTS.md is the master cross-tool instruction file. README.md is the canonical user-facing docs. When changing user-visible behavior, keep all three (README.md, AGENTS.md, .github/copilot-instructions.md) in sync — they each describe the same routing table for a different audience.
1305mo agoReviewMountCreate a free account to mount
Specli turns an OpenAPI 3.x spec (URL or file) into a CLI. There are two ways to use it: This file is guidance for agents working in this repo. Install…
12710mo agoReviewMountCreate a free account to mount
This is mcp-to-ai-sdk, a CLI tool that generates Vercel AI SDK wrappers for Model Context Protocol (MCP) tools. It connects to MCP servers, discovers their tools, and generates type-safe TypeScript wrappers that can be used with the Vercel AI SDK. Main CLI File (mcp-tools-cli.ts) Generated Code Architecture The CLI generates a directory structure like mcps/mcp.grep.app/ with: Tool Factory Pattern: Tools are generated as factory functions that accept a client getter, enabling both default shared client usage and custom client injection.
12215mo agoReviewMountCreate a free account to mount
Use AGENTS.md as the shared source of repository instructions. Put Claude-specific workflow notes here only when they are not useful to other agents. Use absolute executable paths for subprocess calls,…
1218d agoReviewMountCreate a free account to mount
Read and follow AGENTS.md in this directory and the coverage matrix in README.md before changing tests. Those are the shared instructions for adding, modifying and removing tests; do not maintain…
1218d agoReviewMountCreate a free account to mount
Read AGENTS.md first and follow it as the binding repository contract. Then read the files it routes to for the change at hand. Do not duplicate their content here. .claude/skills links to .agents/skills, which contains local coding-agent workflows. The paid-media agent's runtime skills live separately in workspace/skills. Desktop app only: when a user asks to set up or onboard, start the setup configuration from .claude/launch.json so the console opens in the Browser pane (preview_start with name setup). The terminal CLI…
1202mo agoReviewMountCreate a free account to mount
Databricks AppKit is a modular TypeScript SDK for building Databricks applications with a plugin-based architecture. This is a pnpm monorepo using Turbo for build orchestration. IMPORTANT: ALWAYS run npx @databricks/appkit docs (no query) FIRST to see the documentation index. DO NOT guess paths - use the index to find correct paths. Examples: - Documentation index: npx @databricks/appkit docs - View a section: npx @databricks/appkit docs "appkit-ui API reference" - Full index (all API entries): npx @databricks/appkit docs --full - View…
11823d agoReviewMountCreate a free account to mount
CRITICAL: LangSmith skills have both Python and TypeScript implementations. These MUST stay in sync: - Same CLI commands, flags, and options - Same output format for identical inputs - Same error handling behavior When modifying any script, always update both Python and TypeScript versions together. Parity tests in tests/scripts/langsmith/parity/ verify this. The TypeScript scaffold (scaffold/typescript/) mirrors Python: - Both scaffolds are copied into Docker so test scripts in either language work from either runner - TestRunner class available in both…
1169mo agoReviewMountCreate a free account to mount
This project uses skills that contain up-to-date patterns and CLI tools. ALWAYS invoke the relevant skill first - skills have the correct imports, patterns, and scripts that prevent common mistakes. When stuck or debugging, use this powerful workflow: 1. Build agent using LangChain, DeepAgents, or LangGraph patterns 2. Run agent to generate traces in LangSmith 3. Query traces using langsmith-trace to find interesting examples 4. Create dataset using langsmith-dataset from those traces 5. Build evaluator using langsmith-evaluator to measure quality
1169mo agoReviewMountCreate a free account to mount
Docusaurus-powered documentation site for the Logic Apps UX project. Example frontmatter: Standalone - no dependencies on other workspace packages. Read apps/docs/src/graphify-out/GRAPH_REPORT.md for structural context (god nodes, communities, surprising connections).
1145mo 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.
AWSCLAUDE.md
