AGENTS.md

Project overview

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.

Repository structure

packages/          # Published npm packages (need changesets for changes)
  agents/          # Core SDK (see packages/agents/AGENTS.md)
  ai-chat/         # @cloudflare/ai-chat — higher-level AI chat agent
  hono-agents/     # Hono framework integration
  codemode/        # @cloudflare/codemode — experimental code generation

examples/          # Self-contained demo apps (see examples/AGENTS.md)
  playground/      # Main showcase app — all SDK features in one UI (uses Kumo design system)
  mcp/             # MCP server example
  mcp-client/      # MCP client example
  ...              # ~20 examples total

experimental/      # Work-in-progress experiments (not published, no stability guarantees)

site/              # Deployed websites
  agents/          # agents.cloudflare.com (Astro)
  ai-playground/   # Workers AI playground (React + Vite)

guides/            # In-depth pattern tutorials with narrative READMEs (see guides/AGENTS.md)
  anthropic-patterns/
  human-in-the-loop/

openai-sdk/        # Examples using @openai/agents SDK
  basic/ chess-app/ handoffs/ human-in-the-loop/ ...

docs/              # Markdown docs for developers.cloudflare.com (see docs/AGENTS.md)
design/            # Architecture and design decision records (see design/AGENTS.md)
scripts/           # Repo-wide tooling (typecheck, export checks, update checks)

Nested AGENTS.md files

Some directories have their own AGENTS.md with deeper guidance:

File	Scope
packages/agents/AGENTS.md	Core SDK internals — exports, source layout, build, testing, architecture
examples/AGENTS.md	Example conventions — required structure, consistency rules, known issues
guides/AGENTS.md	Guide conventions — how guides differ from examples, README expectations
docs/AGENTS.md	Writing user-facing docs — Diátaxis framework, upstream sync, style
design/AGENTS.md	Design records and RFCs — format, workflow, relationship to docs

Setup

pnpm install       # installs all workspaces

Node 24+ required. Uses pnpm workspaces with Nx for task orchestration, caching, and affected detection.

Commands

Run from the repo root:

Command	What it does
pnpm run build	Builds all packages via Nx (cached, dependency-ordered)
pnpm run check	Full CI check: sherif + export checks + oxfmt + oxlint + typecheck
pnpm run test	Runs all tests via Nx (cached)
pnpm run test:react	Runs Playwright-based React hook tests for agents
pnpm run typecheck	TypeScript type checking across the repo (custom script)
pnpm run format	Oxfmt format all files
pnpm run check:exports	Verifies package.json exports match actual build output
pnpm exec nx affected -t build	Build only packages affected by current changes
pnpm exec nx affected -t test	Test only packages affected by current changes
pnpm exec nx run <project>:build	Build a single project (and its dependencies)

Run an example locally:

cd examples/playground   # or any example
pnpm dev                 # starts Vite dev server + Workers runtime via @cloudflare/vite-plugin

Example apps will normally hot reload when the dev server is running. When the dev server is running, make sure to rebuild changed packages (pnpm run build) to see changes reflected in the running app.

Code standards

TypeScript

• Strict mode enabled (agents/tsconfig)
• Target: ES2021, module: ES2022, moduleResolution: bundler
• verbatimModuleSyntax: true — use explicit import type for type-only imports
• JSX: react-jsx

Linting — Oxlint

Config in .oxlintrc.json. Plugins: react, jsx-a11y, typescript, react-hooks. Key rules:

• no-explicit-any: "error" — never use any, use unknown and narrow
• no-unused-vars: "error" — with varsIgnorePattern: "^_" and argsIgnorePattern: "^_"
• correctness category set to "error" — catches common mistakes
• jsx-a11y rules enabled — accessibility violations are errors
• react-hooks/exhaustive-deps: "warn" — warns on missing hook dependencies

Oxlint does not handle formatting — Oxfmt does.

Formatting — Oxfmt

• Run pnpm run format or rely on lint-staged (auto-formats on commit via husky)
• Config in .oxfmtrc.json (trailingComma: "none", printWidth: 80)

Workers conventions

• Always TypeScript, always ES modules
• wrangler.jsonc (not .toml) for configuration
• All wrangler configs use compatibility_date: "2026-06-11" and compatibility_flags: ["nodejs_compat"]
• Never hardcode secrets — use wrangler secret put or .env
• No native/FFI dependencies (must run in Workers runtime)

Testing

Tests use vitest with @cloudflare/vitest-pool-workers for running inside the Workers runtime.

pnpm run test             # agents + ai-chat unit/integration tests
pnpm run test:react       # Playwright-based React hook tests (agents package)

Test locations:

• packages/agents/src/tests/ — core SDK tests
• packages/agents/src/react-tests/ — React hook tests (Playwright + vitest-browser-react)
• packages/ai-chat/src/tests/ — AI chat tests
• packages/agents/src/tests-d/ — type-level tests (.test-d.ts)

Each test directory has its own vitest.config.ts and (for Workers tests) a wrangler.jsonc.

For a repo-wide rollup of what proves feature X works, at which layer, and which CI run guards it — plus the tracked skip/quarantine debt — see design/test-coverage-matrix.md.

Contributing

Changesets

Changes to packages/ that affect the public API or fix bugs need a changeset:

pnpm exec changeset       # interactive prompt — pick packages, semver bump, description

This creates a markdown file in .changeset/ that gets consumed during release.

Examples, guides, and sites don't need changesets.

Pull request process

CI runs on every PR (pnpm install --frozen-lockfile && pnpm run build && pnpm run check && pnpm exec nx affected -t test); the workflow is in .github/workflows/pullrequest.yml. On push to main the Release workflow (.github/workflows/release.yml) runs the same steps but uses nx run-many -t test as a safety net against under-reported affected projects, then publishes via changesets. All checks must pass.

Generated files

• env.d.ts files are generated by wrangler types — regenerate with pnpm exec wrangler types inside the relevant example/package, don't hand-edit
• pnpm-lock.yaml — regenerated by pnpm install, don't hand-edit

Learned Workspace Facts

• packages/shell/ is published as @cloudflare/shell — an experimental sandboxed JS execution and filesystem runtime for agents, built on the same dynamic Worker loader machinery as @cloudflare/codemode.
• To run code against a Workspace: import stateTools from @cloudflare/shell/workers and DynamicWorkerExecutor/resolveProvider from @cloudflare/codemode; use executor.execute(code, [resolveProvider(stateTools(workspace))]).

Learned User Preferences

• Keep Workspace as a pure durable filesystem — do not embed execution or session logic inside it. Execution is a caller concern wired via @cloudflare/codemode + stateTools.
• When a package boundary feels wrong (e.g., a helper package depending on a larger package just for an adapter), prefer moving the adapter out rather than carrying the dependency.

Boundaries

Always:

• Run pnpm run check before considering work done
• Use import type for type-only imports (enforced by verbatimModuleSyntax)
• Keep examples simple and self-contained — they're user-facing learning material
• Use Cloudflare Workers APIs (KV, D1, R2, Durable Objects, etc.) over third-party equivalents
• Use Workers AI for LLM calls in examples — not third-party APIs like OpenAI or Anthropic

Ask first:

• Adding new dependencies to packages/ (these ship to users)
• Changing wrangler.jsonc compatibility dates across the repo
• Modifying CI workflows

Never:

• Hardcode secrets or API keys
• Add native/FFI/C-binding dependencies
• Use any — Oxlint will reject it
• Use CommonJS or Service Worker format — ES modules only
• Modify node_modules/ or dist/ directories
• Force push to main

Awesome Agent Conventions

A curated field guide to the convention files AI agents read, write, and act on.

22 conventions across 11 categories. From common project instruction files to newer agent-web discovery and trust formats.

Agent tools increasingly rely on plain files in a repository or website root: instructions, memory, rules, tool connections, prompt assets, discovery metadata, and protocol hints. The names are easy to mix up, and the adoption levels vary a lot.

This repo keeps the map practical:

• Know what a file is for. Each entry names the convention, usual filename, primary readers, and spec or source.
• Study real examples. Examples are fetched from public repositories by script, with provenance kept at the top of each file.
• Separate practice from proposal. Maturity labels show what is widely used, what is early, and what is still only proposed.

Contents

• Instruction & context · category page
  • 🟢 AGENTS.md
  • 🟢 CLAUDE.md
  • 🟢 Tool-specific instruction files
  • 🟠 OKF (Open Knowledge Format)
• Memory & state · category page
  • 🟢 MEMORY.md
  • 🟢 Memory Bank
• Spec-driven development · category page
  • 🟢 Spec Kit
  • 🟢 Kiro steering files
• Skills & prompt assets · category page
  • 🟢 SKILL.md
  • 🟢 Prompt asset files
  • 🟢 Claude Code commands
  • 🟢 Copilot prompt & instruction files
• Tooling & connections · category page
  • 🟢 MCP server config
• Rules & ignore files · category page
  • 🟢 Rules files
  • 🟢 AI ignore files
• Design · category page
  • 🟢 DESIGN.md
• Web & discoverability · category page
  • 🟢 llms.txt
  • 🟢 pricing.md
• Agent-web trust · category page
  • 🟠 auth.md
  • 🔵 ai.txt
• Identity & protocols · category page
  • 🟠 Agent Cards (A2A)
• Proposed namespace · category page
  • 🔵 The protocols.md namespace

What counts

This list is intentionally narrow. A file belongs here when it is a convention for agent behavior or agent-readable metadata: instructions, memory, skills, rules, tool config, prompt assets, or web-discovery hints.

Any file type can qualify - .md, .txt, .prompty, .json, dotfiles, or a directory pattern. Human-first project docs such as README.md, CONTRIBUTING.md, SECURITY.md, and CHANGELOG.md stay out unless the file has become an agent convention in its own right.

Maturity tiers

The badge is a claim about adoption, not quality. It keeps a proven convention from being presented the same way as a new idea.

Badge	Tier	Meaning
🟢	Adopted	Used in production by multiple tools, projects, or teams.
🟠	Emerging	Published by a real organization, but still early or limited in adoption.
🔵	Proposed	Publicly described, but without clear adoption beyond the proposal.

Instruction & context

Standalone page: categories/instruction-context.md

	Convention	Files	Read by	Spec
🟢	AGENTS.md	AGENTS.md	Most coding agents - OpenAI Codex, Cursor, Jules, Aider, Gemini CLI, Zed, and others	spec ↗
🟢	CLAUDE.md	CLAUDE.md	Claude Code, and tools that read the Claude memory convention	spec ↗
🟢	Tool-specific instruction files	GEMINI.md AGENT.md QWEN.md WARP.md CONVENTIONS.md copilot-instructions.md	Each file is read by its namesake tool - Gemini CLI, Amp, Qwen Code, Warp, Aider, GitHub Copilot - often alongside or as a bridge to AGENTS.md	spec ↗
🟠	OKF (Open Knowledge Format)	.md	Agents over MCP (okfy, openknowledge, superops okf CLIs); Google's knowledge-catalog ingests bundles	spec ↗

• AGENTS.md - A plain-Markdown "README for agents" - build/test commands, conventions, and gotchas an agent needs before touching the code. The most widely adopted cross-tool instruction file.
• CLAUDE.md - Anthropic's memory file for Claude Code - loaded automatically at session start to carry project commands, style rules, and standing instructions across turns.
• Tool-specific instruction files - Per-tool instruction files that predate or coexist with AGENTS.md. Some tools now default to AGENTS.md while keeping legacy filenames alive, so these variants still matter when auditing real repositories.
• OKF (Open Knowledge Format) - A machine-first organizational knowledge base: a version-controlled folder of typed Markdown files (one concept per file) that any agent reads as ground-truth context. Open-sourced by Google Cloud in 2026 as the content layer to MCP's transport.

Memory & state

Standalone page: categories/memory-state.md

	Convention	Files	Read by	Spec
🟢	MEMORY.md	MEMORY.md	Claude Code's auto-memory - the per-project MEMORY.md index it writes and re-reads each session	spec ↗
🟢	Memory Bank	projectbrief.md productContext.md activeContext.md systemPatterns.md techContext.md progress.md	Cline, Roo Code, and Cursor (via the Memory Bank custom-instructions pattern)	spec ↗

• MEMORY.md - A persistent, agent-maintained index of durable facts - written and re-read across sessions so an agent accumulates project memory instead of relearning each time.
• Memory Bank - Cline's structured memory system - a set of Markdown files an agent reads at the start of every task to reconstruct full project context after its session memory resets. The six files shown are Cline's set; tools like Roo Code use an overlapping but different variant.

Spec-driven development

Standalone page: categories/spec-driven-development.md

	Convention	Files	Read by	Spec
🟢	Spec Kit	constitution.md spec.md plan.md tasks.md	GitHub Spec Kit's slash-command agents (Copilot, Claude, Gemini, Cursor, and more)	spec ↗
🟢	Kiro steering files	product.md structure.md tech.md	AWS Kiro (steering files are largely Kiro-specific)	spec ↗

• Spec Kit - GitHub's spec-driven workflow - a constitution plus per-feature spec → plan → tasks files that drive an agent through structured, reviewable implementation.
• Kiro steering files - Kiro's always-on steering docs - product, structure, and tech files that give the agent persistent project context outside of any single spec.

Skills & prompt assets

Standalone page: categories/skills-prompt-assets.md

	Convention	Files	Read by	Spec
🟢	SKILL.md	SKILL.md	Claude Agent Skills, Claude Code, Amp, Agent Skills-compatible tools	spec ↗
🟢	Prompt asset files	.prompty .prompt system_prompt.txt	Prompty tooling, Azure AI / Semantic Kernel, and apps that load externalized prompts	spec ↗
🟢	Claude Code commands	.md	Claude Code - project .claude/commands/ and user ~/.claude/commands/	spec ↗
🟢	Copilot prompt & instruction files	.prompt.md .instructions.md	GitHub Copilot in VS Code / Copilot CLI	spec ↗

• SKILL.md - A self-contained, model-invoked capability file that tells an agent when to load a reusable procedure and how to execute it.
• Prompt asset files - Externalized prompt files - Prompty's YAML-front-mattered .prompty, plain .prompt templates, and system_prompt.txt - that pull the prompt out of source code so it can be versioned and edited on its own. Only .prompty has a formal spec (prompty.ai); .prompt and system_prompt.txt are ad-hoc externalized-prompt filenames.
• Claude Code commands - A Markdown file Claude Code exposes as a /slash-command - a reusable, version-controlled prompt workflow, with optional frontmatter (allowed-tools, model, argument-hint) and $ARGUMENTS and shell placeholders (@file references are a general Claude Code prompt feature, not command-specific). Now converging with Agent Skills, but still widely committed in its own right.
• Copilot prompt & instruction files - Modular, path-scoped Copilot context: *.instructions.md auto-attach to matching files via an applyTo glob, while *.prompt.md are reusable prompts you invoke by name - the granular cousins of a single .github/copilot-instructions.md.

Tooling & connections

Standalone page: categories/tooling-connections.md

	Convention	Files	Read by	Spec
🟢	MCP server config	.mcp.json	Claude Code, Cursor, VS Code / Copilot, and Claude Desktop - every MCP host reads the same mcpServers schema, though the filename and path differ per tool	spec ↗

• MCP server config - A JSON file that tells an agent which Model Context Protocol servers to launch and how (command, args, env) - making a project's tool and data integrations portable, shareable, and version-controlled across every MCP-capable client.

Rules & ignore files

Standalone page: categories/rules-ignore-files.md

	Convention	Files	Read by	Spec
🟢	Rules files	.cursorrules .mdc .clinerules .clinerules/ (pattern) .windsurfrules	Cursor (.cursorrules / .mdc), Cline (.clinerules/ and legacy .clinerules), Windsurf (.windsurfrules)	spec ↗
🟢	AI ignore files	.aiignore .cursorignore .codeiumignore .aiexclude	JetBrains Junie (.aiignore), Cursor (.cursorignore), Codeium/Windsurf (.codeiumignore)	spec ↗

• Rules files - Per-tool rule files that scope agent behavior - older single-file forms (.cursorrules, .clinerules, .windsurfrules) and newer directory-based, glob-scoped forms (.cursor/rules/.mdc, .clinerules/, .windsurf/rules/.md).
• AI ignore files - gitignore-syntax files that fence an AI agent out of paths - secrets, vendored code, generated output - so they're never sent to the model as context.

Design

Standalone page: categories/design.md

	Convention	Files	Read by	Spec
🟢	DESIGN.md	DESIGN.md	Google Stitch natively; and coding agents (e.g. Claude Code) when pointed at it as design context	spec ↗

• DESIGN.md - A structured, machine-readable design specification - tokens, components, and layout intent - that an agent reads to generate or keep UI consistent with an established system. Open-sourced by Google Labs in 2026 as a cross-tool draft spec.

Web & discoverability

Standalone page: categories/web-discoverability.md

	Convention	Files	Read by	Spec
🟢	llms.txt	llms.txt llms-full.txt (pattern)	Docs sites publish it for LLM tools and crawlers - though no major provider has confirmed reading it	spec ↗
🟢	pricing.md	pricing.md	Agents and LLM browsers fetching a clean, parse-able pricing page	spec ↗

• llms.txt - A proposed-turned-widely-published standard: a root-level Markdown file giving LLMs a curated, link-rich map of a site's docs. Published across hundreds of developer-docs sites - though whether the major LLM providers actually read it remains unproven.
• pricing.md - The Markdown twin of a pricing page - same URL with a .md suffix - so an agent gets structured plans and numbers instead of scraping marketing HTML. A concrete, shipping instance of the page.md pattern.

Agent-web trust

Standalone page: categories/agent-web-trust.md

	Convention	Files	Read by	Spec
🟠	auth.md	auth.md	Agents discovering how to authenticate to a service (early adopters)	spec ↗
🔵	ai.txt	ai.txt	AI training/data-mining crawlers that voluntarily honor AI usage preferences; crawler support is not yet reliable	spec ↗

• auth.md - A Markdown file that tells an agent how to authenticate with a service - discovery of auth endpoints and flows. Shipped by WorkOS as a real, working convention, but adoption beyond it is still early.
• ai.txt - A text file declaring machine-readable consent, licensing, or policy preferences for AI training and data-mining. Spawning popularized the deployed root-file pattern, and a 2026 Internet-Draft now proposes a well-known URI; adoption and crawler obedience are still thin, so it stays 🔵.

Identity & protocols

Standalone page: categories/identity-protocols.md

	Convention	Files	Read by	Spec
🟠	Agent Cards (A2A)	agent-card.json agent.json (pattern)	A2A-compatible agents discovering another agent's capabilities	spec ↗

• Agent Cards (A2A) - The Agent2Agent (A2A) capability card - a JSON document at a well-known path advertising an agent's skills, endpoints, and auth so other agents can discover and call it. Now a Linux Foundation project at v1.0; adoption is growing but early.

Proposed namespace

Standalone page: categories/proposed-namespace.md

	Convention	Files	Read by	Spec
🔵	The protocols.md namespace	proof.md	- (no demonstrated readers; aspirational)	spec ↗

• The protocols.md namespace - A single maintainer's pre-registered namespace of ~74 aspirational .md "protocols" (proof.md, signature.md, reputation.md, …) staked as Schelling points for a future agent web. Published concept, no demonstrated adoption - see the page for the audited, honest caveats.

Maintaining examples

Example files are fetched, not invented. The extractor pulls them from public sources, stores them under conventions/<slug>/examples/<source>/<filename>, and adds a line-1 provenance comment. The examples remain under their upstream owners' licenses and terms; see THIRD_PARTY_EXAMPLES.md before reusing them.

To refresh everything:

pip install -r scripts/requirements.txt
python scripts/extract.py          # fetch real files + rebuild each convention's README
python scripts/build_readme.py     # rebuild this README from scripts/targets.json

Re-running is idempotent. A missing target prints a miss and is skipped. Examples are representative samples: any file over 256 KB (for example, a multi-MB llms-full.txt) is truncated with a marker pointing back to the full source. scripts/targets.json remains the source of truth for conventions that have not been migrated yet; the skill-md pilot uses local convention metadata instead. Edit the relevant source and re-run both scripts.

Shortcut targets are available in the Makefile:

make verify          # schema + generated files + example provenance + links
make extract         # refetch public examples and rebuild generated docs
make license-report  # summarize upstream licenses for vendored examples

CI keeps the generated files and links honest. The verify workflow checks that generated docs match catalog metadata and migrated local metadata, and that every spec, example, and instance URL still resolves on each pull request and weekly. Run the same link check locally with python scripts/check_links.py.

Contributing

Read CONTRIBUTING.md. In short: an entry must pass the filter above and carry evidence for its maturity tier. Add sources to scripts/targets.json for non-migrated conventions, run the scripts, and open a PR. The skill-md pilot uses local convention metadata instead. Do not hand-write example files.

Before proposing adjacent standards, check WATCHLIST.md. Project direction lives in ROADMAP.md.

License

The curation, scripts, and original prose in this repository are MIT. Vendored example files remain under their upstream owners' licenses and terms; see THIRD_PARTY_EXAMPLES.md.