agentleFS

AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Worked for most · soon
CloudflareAGENTS.md

workerd / transform

cloudflare/workerd/src/tests/streams/transform/AGENTS.md

An informal specification of the JS-backed TransformStream as implemented in workerd, derived from — and kept in lockstep with — the test suite in this directory. The tests are the normative artifact. Both the C++ implementation (src/workerd/api/streams/transform.c++ over standard.c++'s TransformStreamDefaultController) and the TypeScript implementation (behind typescript_implemented_streams) are covered. The suite COMPLEMENTS WPT (//src/wpt:streams runs transform-streams/ against both implementations). Probing the 30+ C++ expectedFailures showed most narrow to a handful of root causes (below); several WPT "failures" (properties.any's arg counts/prototype-chain, the…

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / writable

cloudflare/workerd/src/tests/streams/writable/AGENTS.md

An informal specification of the JS-backed writable stream classes as implemented in workerd, derived from — and kept in lockstep with — the test suite in this directory. The tests are the normative artifact. Both the C++ implementation (src/workerd/api/streams/writable.{h,c++} over standard.c++'s WritableImpl/WritableStreamJsController) and the TypeScript implementation (src/per_isolate/webstreams/writable.ts, behind typescript_implemented_streams) are covered. The suite COMPLEMENTS WPT (//src/wpt:streams runs writable-streams/ against both implementations): behaviors WPT already asserts identically on both sides are not duplicated here. The WPT C++ expectedFailures for writable-streams/ in…

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / api

cloudflare/workerd/src/workerd/api/AGENTS.md

All JavaScript APIs exposed to Workers: HTTP, crypto, streams, WebSocket, Cache, KV, R2, SQL, encoding, events, timers, scheduled/alarm handlers.

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / crypto

cloudflare/workerd/src/workerd/api/crypto/AGENTS.md

WebCrypto API + Node.js crypto C++ implementations over BoringSSL. crypto.h defines public JSG types (CryptoKey, SubtleCrypto, CryptoKeyUsageSet). impl.h defines internal CryptoKey::Impl base class with per-algorithm static ImportFunc/GenerateFunc dispatch. Algorithm files implement Impl subclasses. OSSLCALL() macro wraps all BoringSSL calls with error translation.

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / node

cloudflare/workerd/src/workerd/api/node/AGENTS.md

C++ implementations of Node.js built-in modules. Each module = JSG-bound class registered via NODEJS_MODULES(V) macro in node.h. TypeScript counterpart lives in src/node/. Exception: diagnostics-channel only forwards messages to tail workers (publishToTracer); the module itself is in src/node/diagnostics_channel.ts. Some node-internal: modules (dns, inspector, url) are implemented in Rust instead, in src/rust/api/, and registered by register_nodejs_modules() in src/rust/api/lib.rs, not in NODEJS_MODULES. See src/rust/AGENTS.md. Tests in tests/. Naming: <module>-test.js + <module>-test.wd-test; -nodejs- infix when needing compat flags. All tests set compatibilityFlags = ["nodejs_compat",…

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / streams

cloudflare/workerd/src/workerd/api/streams/AGENTS.md

Web Streams API: ReadableStream, WritableStream, TransformStream. See README.md for terse reference (classification, state machines, safety patterns). See docs/streams.md for narrative tutorial. NOTE: C++ code outside this directory does not use jsg::Ref<ReadableStream> or jsg::Ref<WritableStream> directly; it goes through the JsReadableStream / JsWritableStream abstractions in src/workerd/api/js-{readable,writable}-stream.{h,c++}, which hide which stream implementation backs a given stream (and provide JsReadableWritablePair + pipeTo/pipeThrough for abstraction-level pipelines). New C++ consumers of streams should use those abstractions, not the types defined here. Allocating the types defined here…

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / io

cloudflare/workerd/src/workerd/io/AGENTS.md

I/O lifecycle, per-request context, worker/isolate management, actor storage, consistency gates, and compatibility flags.

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / jsg

cloudflare/workerd/src/workerd/jsg/AGENTS.md

See README.md for terse reference (type mappings, macro catalog, error catalog). See docs/jsg.md for narrative tutorial. Macro-driven C++/V8 binding layer: declares C++ types as JS-visible resources/structs with automatic type conversion.

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / server

cloudflare/workerd/src/workerd/server/AGENTS.md

The workerd binary and its server. :workerd (workerd.rs, this package) is a Rust binary over three crates in this directory: This package keeps the config schema (workerd.capnp, compiled-bindings.capnp), the config compiler, the WorkerdApi and the C++ libraries the factory is built from (alarm scheduler, channel tokens, container client, facet tree index, fallback service, actor IDs, JSON logger, V8 platform), and their C++ unit tests. The Rust/C++ boundary. The factory keeps everything that touches the isolate: compiling a worker (WorkerdApi, compatibility…

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / util

cloudflare/workerd/src/workerd/util/AGENTS.md

Shared utility library: data structures, SQLite wrapper, feature gating, logging, thread-local scopes. No workerd-specific API dependencies — consumed across api/, io/, server/.

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / fetch

cloudflare/workerd/src/wpt/fetch/AGENTS.md

WPT fetch/api runs in two cells, one per streams implementation: Both cells pin the same compatibility flags otherwise (strip_bom_in_read_all_text). Most entries in either config are fetch API divergences that apply to both implementations (missing CORS, cache modes, redirect handling, header validation, unimplemented methods, ...). They are duplicated in both configs and kept identical. Subtests whose result depends on the streams implementation. A row here means the two configs differ for that subtest: it is an expectedFailures or disabledTests entry in…

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / types

cloudflare/workerd/types/AGENTS.md

Generates @cloudflare/workers-types .d.ts files from C++ and Rust JSG RTTI (via jsg/rtti.capnp) + hand-written defines/*.d.ts. Rust descriptions come from TypeInfo and typed module registration in src/rust/jsg/; internal module registration does not make a type an ambient root. A workerd-hosted Worker extracts RTTI at runtime per compat-date; TypeScript transforms post-process into ambient and importable outputs. CI validates generated-snapshot/ matches. - Structure.tsName / StructureType.tsName supply the emitted declaration and reference name. When empty, the generator derives the name from fullyQualifiedName, which remains…

9.1k8mo agoReviewMountCreate a free account to mount
CloudflareReads credentialsAGENTS.md

agents

cloudflare/agents/AGENTS.md

Cloudflare Agents SDK — a framework for building stateful AI agents on Cloudflare Workers. This is a monorepo containing the core SDK packages, examples, guides, sites, and documentation. Some directories have their own AGENTS.md with deeper guidance: Node 24+ required. Uses pnpm workspaces with Nx for task orchestration, caching, and affected detection. Run from the repo root: Run an exampl

Steady3 mentions in 2 weeks

No other project uses it yet

6k12d agoReviewMountCreate a free account to mount
CloudflareReads credentialsAGENTS.md

agents / agent-think

cloudflare/agents/agent-think/AGENTS.md

A Think agent (@cloudflare/think) that reproduces and fixes cloudflare/agents GitHub issues inside a container-backed @cloudflare/workspace VFS. Anyone trusted on the repo triggers it from an issue comment: e.g. @agent-think reproduce this issue or @agent-think open a PR fixing this. It runs the matching skill (reproduce / open-pr) in a real Linux container and reports back on the issue as the agent-think GitHub App — never impersonating the triggering user. - Replace CI-runner automations (the /repro + /pr Actions shape from…

Steady3 mentions in 2 weeks

No other project uses it yet

6k12d agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

agents / design

cloudflare/agents/design/AGENTS.md

Internal design records — the "why" behind decisions in this repo and its libraries. This is the Diátaxis explanation quadrant: architecture rationale, tradeoffs, and alternatives considered. Living documents that describe how a concept or subsystem works right now. Named by topic: state.md, mcp.md, visuals.md. These are the primary entry point — a contributor looking for "how does state work" should open one file and get the full picture. Design docs get updated as the implementation evolves. They always reflect the…

Steady3 mentions in 2 weeks

No other project uses it yet

6k12d agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

agents

cloudflare/agents/docs/AGENTS.md

User-facing documentation for the Agents SDK monorepo. Each package owns the directory under docs/ matching its unscoped package name. These markdown files are manually synced to developers.cloudflare.com/agents/ where applicable. We follow Diátaxis to keep docs focused. Every doc should have a clear primary type: The fourth Diátaxis type — explanation ("understand why") — lives in /design, not here. If you're writing about why something was designed a certain way, put it there. If you're writing about how to use something,…

Steady3 mentions in 2 weeks

No other project uses it yet

6k12d agoReviewMountCreate a free account to mount
CloudflareReads credentialsAGENTS.md

agents / examples

cloudflare/agents/examples/AGENTS.md

Self-contained demo apps that show how to use the Agents SDK. These are user-facing learning material — keep them simple, clear, and consistent. Each example should focus on one feature or concept (e.g., MCP servers, email routing, workflows). The exception is playground/, which is the kitchen-sink showcase covering the full spread of SDK features in a single app. Most examples have both a frontend and a backend. This makes them immediately runnable and visually demonstrable — users can pnpm run…

Steady3 mentions in 2 weeks

No other project uses it yet

6k12d agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

agents / webmcp-react

cloudflare/agents/examples/webmcp-react/AGENTS.md

WebMCP should work out of the box. If it does not:

Steady3 mentions in 2 weeks

No other project uses it yet

6k12d agoReviewMountCreate a free account to mount
CloudflareReads credentialsAGENTS.md

agents / guides

cloudflare/agents/guides/AGENTS.md

In-depth, pattern-oriented tutorials — runnable apps with substantial narrative READMEs that teach how to build a particular kind of agent application. If it demonstrates a single feature, it belongs in /examples. If it teaches an approach or pattern, it belongs here. Guides are runnable apps with the same structural conventions as examples: The README is the guide. The code is the supporting material. A guide README should walk a reader through the application, explaining both what the code does and…

Steady3 mentions in 2 weeks

No other project uses it yet

6k12d agoReviewMountCreate a free account to mount
CloudflareReads credentialsAGENTS.md

agents / agents

cloudflare/agents/packages/agents/AGENTS.md

The core Agents SDK, published to npm as agents. This is the most complex package in the monorepo. Each export maps to a public entry point that users import from. These are the boundaries of the public API — changes here need a changeset.

Steady3 mentions in 2 weeks

No other project uses it yet

6k12d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About AGENTS.md

What is AGENTS.md?

An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.

Where does it go?

At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.

What should it contain?

Setup and test commands, code style, and the rules a new contributor would need to know.

Does Claude Code read it?

Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.