agentmods.dev

vibesdk AGENTS.md

A set of instructions for coding agents working on a Cloudflare project with a React interface and a Worker backend. It explains the project tools, local setup, frontend work, data fetching, and checks.

In plain words
What is it for?
Use it when installing dependencies, starting local development, running tests, checking types, linting, or building the Cloudflare application.
Why use it?
It gives agents the repository-specific commands and rules they need, reducing setup mistakes and missed verification steps.

Instructions file for CodexOpenCode

5.3k +5 2d ago A scan 1,600 tokens original MIT
View the source file cloudflare/vibesdk
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/cloudflare/vibesdk/agents-md
Clone the repo
git clone --depth 1 https://github.com/cloudflare/vibesdk

Made for: Codex, OpenCode.

Per session 1,600 This file is loaded in full into every session.
When invoked 1,600 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01600 $0.01600
Opus 5 $0.00800 $0.00800
Sonnet 5 $0.00320 $0.00320
Haiku 4.5 $0.00160 $0.00160

Measured 2d ago against content hash d2ccf206b10b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibesdk AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Tooling

  • Use Bun from the repository root. The tracked lockfile is bun.lock, the space workspace dependency uses workspace:*, and install/build hooks invoke Bun even when started through npm.
  • bun run setup is the interactive Cloudflare/resource bootstrap. Local development expects the generated .dev.vars; never commit .dev.vars* or .prod.vars.
  • bun run dev starts the React frontend and Worker together through @cloudflare/vite-plugin at http://localhost:5173. There is no separate Worker dev command.
  • bun run dev:browser is an optional local Chromium sidecar for the think agent's browser-console tool; absence only produces a warning.

Verification

  • Root checks: bun run typecheck, bun run lint, bun run test, bun run build.
  • bun run build builds space and the Vite/Worker bundle; it does not typecheck. Run bun run typecheck separately.
  • Focus a root test with bunx vitest run path/to/file.test.ts; test execution uses the Workers pool and wrangler.test.jsonc.
  • The root Vitest suite excludes all sdk/test/** and container/monitor-cli.test.ts. SDK tests use Bun: bun run --cwd sdk test.
  • SDK integration tests require a running root dev server and VIBESDK_INTEGRATION_API_KEY; run bun run --cwd sdk test:integration. They can take 5-10 minutes; VIBESDK_INTEGRATION_RUN_PREVIEW=1 enables the slower preview case.
  • Root typecheck/lint do not validate space or sdk. For touched packages run bun run --cwd space typecheck / bun run --cwd space build and bun run --cwd sdk package as appropriate.
  • ESLint checks only src/** and worker/** and deliberately ignores tests; do not treat bun run lint as repository-wide validation.
  • Pre-commit typechecks staged TypeScript and runs related Vitest tests. RUN_ALL_TESTS=1 selects its broader suite; SKIP_TESTS=1 bypasses the hook.

Frontend UI

  • Tailwind CSS v4 via CSS-first setup in src/index.css (@import 'tailwindcss', @theme, Kumo tokens); no tailwind.config.*.
  • Prefer @cloudflare/kumo for new UI. List components with bun kumo ls; component docs via bun kumo doc Button (swap name as needed). Legacy shadcn/Radix under src/components/ui/ still exists—do not add new primitives there when Kumo covers the case.
  • Icons: @phosphor-icons/react. Dark mode is data-mode="dark" on the root (not a class strategy).
  • Path aliases: @/* → src/*, shared/*, worker/* (see tsconfig.app.json).

Read the full file on GitHub · 55 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 55 lines · 1,600 tokens per session scan A d2ccf206b10b

Subscribe to this mod's changes

vibesdk AGENTS.md is an instructions file published in the GitHub repository cloudflare/vibesdk (5,343 stars, last pushed 2d ago), licensed MIT. It adds 1,600 tokens to every session, about $0.0080 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

aicloudflare-workerscoding-agentdurable-objectstext-to-appvibe-coding
Related

Other instructions, from other repositories

sark AGENTS.md

AGENTS.md instructions for Arjia-Labs/sark, covering agents.md — deploying sark, rules, phase 0 — prerequisites, phase 1 — clone and verify the tree and phase 2 — box credentials.

Arjia-Labs/sark · 2,580 tokens

munkel CLAUDE.md

Instructions for limehq/munkel, covering claude.md, monorepo layout, commands, macos development specifics and deploy.

limehq/munkel · 2,131 tokens

cloudbox AGENTS.md

Instructions for acoyfellow/cloudbox, covering cloudbox agent guide, canonical commands, deploy model, cloudflare account boundaries and required production secrets.

acoyfellow/cloudbox · 670 tokens

ctxlayer CLAUDE.md

Instructions for stevenn/ctxlayer, covering ctxlayer — claude code briefing, what runs where, architecture pointers, how a claude session should work in this repo and conventions.

stevenn/ctxlayer · 5,018 tokens

sdl-mcp AGENTS.md

AGENTS.md instructions for GlitterKill/sdl-mcp, covering agents.md - sdl-mcp knowledge base, structure, where to look, architecture and conventions.

GlitterKill/sdl-mcp · 3,404 tokens

ctxlayer AGENTS.md

Instructions for stevenn/ctxlayer, covering working in this repo as an agent, golden path for any change, where things live, module rules and adding an endpoint.

stevenn/ctxlayer · 1,825 tokens