How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
CloudflareAGENTS.mdcloudflare/moltworker/AGENTS.md
types if needed in `src/types.ts` 3. Update client API in `src/client/api.ts` if frontend needs it 4. Add tests ### Adding a New Environment Variable 1. Add to `MoltbotEnv` interface in `src/types.ts
open-gsdAGENTS.mdopen-gsd/gsd-core/docs/AGENTS.md
anything less stays `[ASSUMED]` --- ### gsd-ui-researcher **Role:** Produces UI design contracts for frontend phases. | Property | Value | |----------|-------| | **Spawned by** | `/gsd-ui-phase` | | **Parallelism** | Single instance | | **Tools** | Read, Write, Edit, Bash, Grep, Glob
CloudflareAGENTS.mdcloudflare/vinext/AGENTS.md
# Agent Guidelines Instructions for AI agents working on this codebase. --- ## Project Overview **vinext** is
freecodexyzAGENTS.mdfreecodexyz/free-code/AGENTS.md
runtime polymorphism only at genuine runtime boundaries such as providers, storage backends, platform services, frontends, and integrations. - **MUST NOT** add allocation, virtual dispatch, type erasure, reference counting, or synchronization unless
maximhqAGENTS.mdmaximhq/bifrost/AGENTS.md
# AGENTS.md — Bifrost AI Gateway > Context for AI agents (Claude Code, Copilot, Cursor, etc.) working
OpenCoworkAIAGENTS.mdOpenCoworkAI/open-codesign/AGENTS.md
package.json`, workspace manifests, and `pnpm-lock.yaml`. Read those files instead of trusting stale docs. ### Frontend - React + Vite + Tailwind v4 + CSS variables. - State uses Zustand. Do not introduce Redux, Recoil, or MobX
GreptimeTeamAGENTS.mdGreptimeTeam/greptimedb/AGENTS.md
repository; most crates live under `src/` (plus `tests-fuzz`, `tests-integration`, `tests/runner`). Key areas: - **Frontend / protocol**: `src/frontend/` (request orchestration), `src/servers/` (wire protocols), `src/sql/` (SQL parsing) - **Storage engines**: `src/mito2/` (main time
Nasiko-LabsAGENTS.mdNasiko-Labs/nasiko/ui/AGENTS.md
AGENTS.md — `oss/ui` `oss/ui` is a zero-build, vanilla-JS web-component frontend: no bundler, no framework, no `node_modules` at runtime. Every page is native ES modules + CSS, embedded directly
MicrosoftAGENTS.mdmicrosoft/aspire/AGENTS.md
csharp // Parse resource log lines emitted as: // [2026-05-10T18:34:22.123Z] frontend stdout: Now listening on: http://localhost:5221 // The message can contain additional ':' characters, so split
huangruitengAGENTS.mdhuangruiteng/loopx/AGENTS.md
change is finalized. ## Product Delivery Completeness For product changes, identify affected user entry points (frontend, Lark, CLI) while planning. Inspect existing settings and capability editors before calling a configuration change
kenn-ioAGENTS.mdkenn-io/agentsview/AGENTS.md
toolchains, CI build tags, or dependencies | `docs/agents/build.md` | | S3 ingest, `S3Provider`, or `Source.S3Discovery` | `docs/agents/s3-providers.md` | | Any frontend file | `frontend/AGENTS.md` | | Frontend controls, styling, or reusable components | `frontend/AGENTS.md` and `DESIGN.md` | The `README.md` and `Makefile
kenn-ioAGENTS.mdkenn-io/agentsview/frontend/AGENTS.md
Vitest, tsdown, Oxlint, Oxfmt, and Vite Task. Vite+ wraps runtime management, package management, and frontend tooling in a single global CLI called `vp`. Vite+ is distinct from Vite
CloudflareAGENTS.mdcloudflare/agents/agent-think/AGENTS.md
issue. - **Reproductions a human can see.** Every repro deploys with a minimal Vite frontend — click the `workers.dev` link, press _Trigger bug_, watch expected-vs-actual in the page (deployed
CloudflareAGENTS.mdcloudflare/agents/examples/AGENTS.md
features in a single app. ## Example shape Most examples have both a frontend and a backend. This makes them immediately runnable and visually demonstrable — users can `pnpm run start
21st-devAGENTS.md21st-dev/1code/openspec/AGENTS.md
tasks.md:** ```markdown ## 1. Implementation - [ ] 1.1 Create database schema - [ ] 1.2 Implement API endpoint - [ ] 1.3 Add frontend component - [ ] 1.4 Write tests ``` 5. **Create design.md when needed:** Create `design.md
VercelAGENTS.mdvercel-labs/scriptc/AGENTS.md
touches their organization; new tests should follow this convention. ## Where things live - `packages/compiler` — the frontend (tsc API to IR), typed IR, validator, serializer, and LLVM and C backends. - `packages/runtime
VercelAGENTS.mdvercel/eve/apps/templates/personal-agent-template/AGENTS.md
README](README.md) — Quick start and feature overview ## Eve Framework This project deploys its Nuxt frontend and eve agent as peer Vercel services through `vercel.ts`. Before writing agent code, read
CloudflareAGENTS.mdcloudflare/vibesdk/AGENTS.md
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
TencentCloudAGENTS.mdTencentCloud/Octop/AGENTS.md
PostgreSQL via `psycopg` / `psycopg_pool` | | LLM runtime | `octop-harness` (LangGraph) | | Gateway | `octop-gateway` | | Frontend | React 18 + TypeScript + Vite | | Package manager | uv — always `uv run pytest`, never bare `pytest` | | API docs
loopljAGENTS.mdlooplj/axonhub/AGENTS.md
files should be stored in `.agent/summary` directory if available. ## Configuration - Backend API: port 8090, Frontend dev server: port 5173 (proxies to backend). - Configuration: `conf/conf.go` (YAML + env var), SQLite by default
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.
