Guidelines for AI agents working on this codebase. This is a Cloudflare Worker that runs OpenClaw (formerly Moltbot/Clawdbot) in a Cloudflare Sandbox container. It provides: - Proxying to the OpenClaw gateway (web UI + WebSocket) - Admin UI at /_admin/ for device management - API endpoints at /api/* for device pairing - Debug endpoints at /debug/* for troubleshooting Note: The CLI tool and npm package are now named openclaw. Config files use .openclaw/openclaw.json. Legacy .clawdbot paths are supported for backward…
Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers environment. Requires CDP_SECRET env var and cdpUrl configured in browser.profiles.
- README.md — what this repo is and how the pieces fit together. - CONTRIBUTING.md — public contribution paths. - COLLABORATORS.md — setup, checks, commit and pull request conventions. The canonical source for the day-to-day workflow. - docs/README.md — design specification. Forward- looking; treat as intent, not as a description of main. - docs/08capnwebinterface.md — the RPC contract between the Durable Object and computerd. Required reading before touching packages/rpc or packages/computer. - Each package's own README.md — implementation status and…
capnweb RPC patterns for this repo, with a heavy focus on stub lifecycle and disposal. Load when touching anything that crosses the Durable Object ↔ computerd boundary: packages/rpc, packages/computer, the computerd client, or the Durable Object server. Triggers include "capnweb", "RpcTarget", "stub", "RPC wire", "promise pipelining", "stub disposal", "RpcPromise".
Index of Cloudflare-platform skills relevant to this repo. Load when working on anything that touches Workers, Durable Objects, wrangler, the sandbox SDK, the agents SDK, or other Cloudflare platform surface. Triggers include "Cloudflare", "Workers", "Durable Object", "wrangler", "KV", "R2", "D1", "Vectorize", "Containers", "sandbox".
Debug computerd in real-FUSE mode end-to-end without workerd, vitest-pool-workers, or wrangler in the loop. Boot the linux-x64 binary in a privileged docker container, drive its capnweb /api endpoint from Node, simulate DO-side sync from a SQLiteTestStorage, and isolate FUSE-related deadlocks. Load when a real-FUSE bug reproduces locally but unit tests pass, when the harness vitest tests hang against a real container, or when you need to attribute a wedge to FUSE vs sync vs exec.
Style guidance for the written word. Use when asked to write code comments, commit messages, pull requests, READMEs, or documentation. Triggers might be phrases like "write a commit", "document this", or "add a README".
Describes how to write pull/merge requests. Use when asked to write or edit a pull request or merge request description. This skill is not relevant to commit messages.
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
Instructions for AI agents working on this codebase. vinext is a Vite plugin that reimplements the Next.js API surface, with Cloudflare Workers as the primary deployment target. The goal: take any Next.js app and deploy it to Workers with one command. vinext reimplements the Next.js API surface using Vite, with Cloudflare Workers as the primary deployment target. The goal is to let developers keep their existing Next.js code and deploy it to Workers. This is a required step for all…
Migrates Next.js projects to vinext (Vite-based Next.js reimplementation). Load when asked to migrate, convert, or switch from Next.js to vinext. Handles compatibility scanning, package replacement, Vite config generation, ESM conversion, and deployment setup (Cloudflare Workers natively, other platforms via Nitro).
Subdirectory AGENTS.md files provide component-specific context (key classes, where-to-look tables, local conventions and anti-patterns). - Suggest updates to AGENTS.md when you find new high-level information - You should always determine if the current repository was checked out standalone or as a submodule of the larger workers project. - If checked out as a submodule, be aware that there is additional documentation and context in the root of that repository that is not present here. Look for the ../../README.md, ../../AGENTS.md, and…
Custom Bazel rules (wd_* macros) for C++, TypeScript, Rust, Cap'n Proto, and test orchestration. Uses bzlmod (MODULE.bazel), not WORKSPACE. This is build system definitions, NOT build output (bazel-bin/). Conventions: //tools/clang-tidy:workerd-lint builds a shared-object clang-tidy plugin that adds workerd-specific static checks: - jsg-visit-for-gc: flags JSG resource types whose visitable fields (jsg::Ref, jsg::JsRef, jsg::V8Ref, jsg::Function, jsg::Promise, jsg::Value, etc., plus kj::Maybe/Array/Vector/ OneOf and jsg::Optional wrappers thereof) are missing from visitForGc(). - workerd-angled-includes - requires includes of workers/capnproto code from different directories to use…
Mandatory rules for running bazel tests during development. Load this skill before running any bazel test command, especially when validating fixes or verifying regression tests. Prevents false confidence from cached results, filter flags that silently match nothing, and partial test runs that miss breakage.
Commit categorization rules for changelogs and "what's new" summaries. MUST be loaded before categorizing commits in changelog or whats-new commands. Provides the canonical path-based category table used to group commits by area.
After completing any task that took more than ~5 tool calls, or after long-running builds/tests finish, load this skill and deliver a dad joke to lighten the mood. Also load before any user-requested joke, pun, or limerick. Never improvise jokes without loading this skill first.
How to find, build, and run tests in workerd. Covers wd-test, kj_test target naming, bazel query patterns, and common flags. Also covers parent project integration tests if workerd is used as a submodule. Load this skill when you need to locate or run a test and aren't sure of the exact target name or invocation.
Identifies the local user's GitHub account and git identity before performing code reviews. Load this skill at the start of any PR review, code review, or commit log analysis so findings can be framed relative to the user's own prior comments, commits, and approval status.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
CloudflareAGENTS.md