How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
CloudflareAGENTS.mdcloudflare/workerd/src/per_isolate/AGENTS.md
guarantee — and what they do not.** Primordials are an **internal correctness** mechanism, not a security sandbox. The hard security boundary is the V8 isolate: separate address spaces, no shared mutable
CloudflareAGENTS.mdcloudflare/workerd/src/tests/streams/AGENTS.md
src/workerd/api/tests/ts-webstreams-test.js` — TypeScript-impl internals (native/buffer/iterable bodies ARE ts streams, pumpTo); single-implementation by nature. - Security regression singles in `src/workerd/api/tests/` (streams-byob-close-reentry, streams-byob-concurrent-readatleast, streams-byte-cancel
CloudflareAGENTS.mdcloudflare/workerd/src/tests/streams/htmlrewriter/AGENTS.md
api/tests htmlrewriter-transform-cancel-test.js (cancel-before-read ×50 UAF regression) stays where it is, per the security-regression policy
CloudflareAGENTS.mdcloudflare/workerd/src/tests/streams/piping/AGENTS.md
pipe-write-special-buffer-test.js (deleted), streams-error-edge-cases-test.js (−2), streams-backpressure-test.js (−1), api/streams/streams-test.js (−2; partiallyReadStream and inspect remain). The security regression files remain authoritative and separate: identity-transform-stream-uaf, pipe-source-error-uaf, identity-transform
CloudflareAGENTS.mdcloudflare/workerd/src/tests/streams/readable-byte/AGENTS.md
readable suite), streams-tee-edge-cases-test.js, streams-respond-test.js, streams-byob-edge-cases-test.js, streams-no-auto-allocate-test.js. streams-test.js shrank to its writable/TransformStream remnant. The security regression files remain authoritative and separate: autovuln-37/60/131/132/148/319, streams-byte-cancel-uaf, streams-byte-handlePush
CloudflareAGENTS.mdcloudflare/workerd/src/workerd/server/AGENTS.md
init: `startServices()` then `listenOnSockets()` | | `workerd.capnp` | Config schema: `Config`, `Service`, `Worker`, `Socket`, `Extension`. Capability-based security model | | `workerd-api.h/c++` | `WorkerdApi`: registers all JS API types with JSG, compiles modules/globals, extracts
max-sixtyAGENTS.mdmax-sixty/worktrunk/.github/AGENTS.md
Worktrunk CI automation The generic security model is in https://github.com/max-sixty/tend/blob/main/docs/security-model.md. This file records the Worktrunk-specific boundaries; verify current GitHub settings before changing them. ## Bot identity worktrunk
NirDiamantAGENTS.mdNirDiamant/Prompt_Engineering/AGENTS.md
engineering, from basic prompt structure through chain-of-thought, self-consistency, task decomposition, prompt security and systematic prompt evaluation. Each notebook explains one technique, implements it, and shows what changes
logancyangAGENTS.mdlogancyang/obsidian-copilot/AGENTS.md
order: 1. **Correctness** — logic errors, data loss, unhandled failure paths, concurrency hazards. 2. **Security** — authorization bypass, injection, secrets or private data leaving the codebase. 3. **Breaking changes and migrations** — changed
trailofbitsAGENTS.mdtrailofbits/skills/AGENTS.md
plugin](https://github.com/EveryInc/compound-engineering-plugin) - Production plugin structure - [getsentry/skills](https://github.com/getsentry/skills) — Production Sentry skills; `security-review` is a standout routing + progressive disclosure example **For Claude:** Use the `claude-code-guide
MicrosoftAGENTS.mdmicrosoft/Security-101/AGENTS.md
AGENTS.md ## Project Overview **Security-101** is a beginner-friendly cybersecurity curriculum created by Microsoft. The project is a documentation-based learning resource that teaches fundamental cybersecurity concepts through structured modules
MicrosoftAGENTS.mdmicrosoft/Security-101/translations/ar/AGENTS.md
AGENTS.md ## نظرة عامة على المشروع **Security-101** هو منهج تعليمي مبتدئ في مجال الأمن السيبراني تم إنشاؤه بواسطة Microsoft. المشروع عبارة عن مورد تعليمي يعتمد على الوثائق ويعلم مفاهيم الأمن
MicrosoftAGENTS.mdmicrosoft/Security-101/translations/bg/AGENTS.md
AGENTS.md ## Преглед на проекта **Security-101** е учебна програма за начинаещи в областта на киберсигурността, създадена от Microsoft. Проектът представлява ресурс за обучение, базиран на документация, който преподава основни концепции
MicrosoftAGENTS.mdmicrosoft/Security-101/translations/bn/AGENTS.md
AGENTS.md ## প্রকল্পের সংক্ষিপ্ত বিবরণ **Security-101** হলো Microsoft দ্বারা তৈরি একটি নবীন-বান্ধব সাইবার নিরাপত্তা পাঠক্রম। এই প্রকল্পটি একটি ডকুমেন্টেশন-ভিত্তিক শিক্ষার উৎস যা গঠনমূলক মডিউলের মাধ্যমে মৌলিক সাইবার নিরাপত্তা
MicrosoftAGENTS.mdmicrosoft/Security-101/translations/br/AGENTS.md
AGENTS.md ## Visão Geral do Projeto **Security-101** é um currículo de cibersegurança para iniciantes criado pela Microsoft. O projeto é um recurso de aprendizado baseado em documentação que ensina conceitos
MicrosoftAGENTS.mdmicrosoft/Security-101/translations/cs/AGENTS.md
AGENTS.md ## Přehled projektu **Security-101** je přívětivý vzdělávací program o kybernetické bezpečnosti vytvořený společností Microsoft. Projekt je dokumentačním zdrojem, který učí základní koncepty kybernetické bezpečnosti prostřednictvím strukturovaných modulů. Je nezávislý
MicrosoftAGENTS.mdmicrosoft/Security-101/translations/da/AGENTS.md
AGENTS.md ## Projektoversigt **Security-101** er et begyndervenligt cybersikkerhedsforløb skabt af Microsoft. Projektet er en dokumentationsbaseret læringsressource, der underviser i grundlæggende cybersikkerhedskoncepter gennem strukturerede moduler. Det er leverandøruafhængigt og designet
MicrosoftAGENTS.mdmicrosoft/Security-101/translations/de/AGENTS.md
AGENTS.md ## Projektübersicht **Security-101** ist ein anfängerfreundliches Cybersecurity-Curriculum, das von Microsoft erstellt wurde. Das Projekt ist eine dokumentationsbasierte Lernressource, die grundlegende Cybersecurity-Konzepte durch strukturierte Module vermittelt
MicrosoftAGENTS.mdmicrosoft/Security-101/translations/el/AGENTS.md
AGENTS.md ## Επισκόπηση Έργου Το **Security-101** είναι ένα εκπαιδευτικό πρόγραμμα κυβερνοασφάλειας για αρχάριους, που δημιουργήθηκε από τη Microsoft. Το έργο αποτελεί έναν πόρο μάθησης βασισμένο σε τεκμηρίωση, που διδάσκει θεμελιώδεις
MicrosoftAGENTS.mdmicrosoft/Security-101/translations/en/AGENTS.md
AGENTS.md ## Project Overview **Security-101** is a beginner-friendly cybersecurity curriculum developed by Microsoft. This project is a documentation-based learning resource that introduces fundamental cybersecurity concepts through structured modules
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.
