agentleFS

Find the best CLAUDE.md, AGENTS.md and Claude skills

One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.

Worked for most · soon
CloudflareAGENTS.md

workerd / strategies

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

An informal specification of the two WHATWG queuing strategy 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/readable.h) and the TypeScript implementation (src/per_isolate/webstreams/strategies.ts, behind typescript_implemented_streams) are covered. The WPT streams/queuing-strategies.any.js runs against both implementations; its 12 C++ expectedFailures in src/wpt/streams-test.ts correspond exactly to ledger entries #1–#6 below — the suite pins what the C++ side actually does where…

9.2k8mo agoReviewMountCreate a free account to mount
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…

9.2k8mo 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…

9.2k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / url

cloudflare/workerd/src/tests/url/AGENTS.md

An informal specification of URL and URLSearchParams as implemented in workerd, kept in lockstep with the test suite in this directory. The tests are the normative artifact. The cells run the same modules (url-modules.capnp) against the C++ implementations and the TypeScript one: which-impl.js reads the flags; a cell's USING_TS_IMPL binding says which implementation it means to run. enable_fast_jsg_struct is not pinned: the @ and @all-compat-flags variants run each cell with it off and on. The TypeScript implementation honors the dated…

9.2k8mo agoReviewMountCreate a free account to mount
CloudflareAGENTS.md

workerd / urlpattern

cloudflare/workerd/src/tests/urlpattern/AGENTS.md

An informal specification of URLPattern as implemented in workerd, kept in lockstep with the test suite in this directory. The tests are the normative artifact. The cells run the same modules (urlpattern-modules.capnp) against the C++ implementations and the TypeScript one: which-impl.js reads the flags; a cell's USING_TS_IMPL binding says which implementation it means to run. enable_fast_jsg_struct is not pinned: the @ and @all-compat-flags variants run each cell with it off and on. The TypeScript implementation honors the dated flags above…

9.2k8mo 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.

9.2k8mo 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.

9.2k8mo 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",…

9.2k8mo 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…

9.2k8mo 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.

9.2k8mo 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.

9.2k8mo 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…

9.2k8mo 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/.

9.2k8mo 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…

9.2k8mo 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…

9.2k8mo 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

6k13d 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

6k13d agoReviewMountCreate a free account to mount
CloudflareSkill

open-pr

cloudflare/agents/agent-think/skills/open-pr/SKILL.md

Take a cloudflare/agents GitHub issue plus any repro findings and one-shot a fix PR — branch, change, test, push, and open the PR linked to the issue.

62 projects use a version of this

6k13d agoReviewMountCreate a free account to mount
CloudflareReads credentialsSkill

reproduce

cloudflare/agents/agent-think/skills/reproduce/SKILL.md

Reproduce a cloudflare/agents GitHub issue by scaffolding a minimal Agents/Worker project and deploying it to a temporary Cloudflare account, then report findings back on the issue.

6 projects use a version of this

6k13d 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

6k13d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

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.