How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
benavlabsAGENTS.mdbenavlabs/vibe-check/AGENTS.md
They are non-negotiable. ## Secrets - NEVER put API keys, database credentials, or tokens in frontend code (anything under src/, app/, pages/, components/, public/) - NEVER put secret keys in environment variables
Samopal88AGENTS.mdSamopal88/ai-platform/AGENTS.md
Execution Rules ### File operations - Write only inside SAFE_DIRS: `sandbox/` `tests/` `docs/` `storage/` `scripts/` `frontend/` `backend/app/services/` `backend/app/api/` `backend/app/models/` `backend/app/core/` `backend/app/generated/` - Fallback for unknown paths: write to `sandbox/ ` - Verify file exists
extra-orgAGENTS.mdextra-org/extra/AGENTS.md
bearing (see §3 rule 11). There is no separate `src/agentplatform/` package and no standalone `frontend/` app in active use — the official React web client is served from `src/agent_manager/api/static/widget
loveramarois-byteAGENTS.mdloveramarois-byte/council-lab/AGENTS.md
Preserve existing standard-mode behavior unless explicitly changed. - Run all relevant backend, frontend, evaluation, migration, and security tests. - Report commands run and checks that could not be executed
RebornQAGENTS.mdRebornQ/AnyRouter-Transparent-Proxy/AGENTS.md
service; entry `app.py`, settings `config.py`, logic in `services/`, routes in `routers/`, helpers in `utils/`. - `frontend/` Vue 3 + TypeScript dashboard; pages in `views/`, shared UI in `components/`, API wrappers in `services
JetBrainsAGENTS.mdJetBrains/klibs-io/AGENTS.md
Toolchain plugins (git-properties, jib) project.yaml # Kotlin Toolchain project root (module list + plugin registrations) frontend/ # Frontend app (React) ``` Module structure follows "module by feature". Each core module
JetBrainsAGENTS.mdJetBrains/klibs-io/frontend/AGENTS.md
AGENTS.md Next.js 14 (App Router) frontend for klibs.io. React 18 + TypeScript, JetBrains `@rescui/*` design system. ## Setup ```bash npm install cp .env.example .env.local # NEXT_PUBLIC_API_URL points at the backend
itseffiAGENTS.mditseffi/agentic-os/AGENTS.md
strategy/` | crux-diagnosis, competitor-analysis, structured-product-strategy, limit-based-strategy, value-chain-mapping, frontend-design, backend-design | Strategic planning | | `meetings/` | ideas-summary, hidden-agendas, influence, meeting-power-dynamics | Meeting
TheBeardedBearSASAGENTS.mdTheBeardedBearSAS/claude-craft/docs/AGENTS.md
Docker environments with proper networking, volumes, and dependencies. Helps with: - Service orchestration - Network segmentation (frontend, backend, data) - Volume management and persistence - Health checks and dependencies - Environment-specific overrides (dev, staging
gintaszAGENTS.mdgintasz/unigent/AGENTS.md
core MUST house all reusable language/runtime logic. Private harness adapters and the `unigent-cli` frontend contain only the minimum translation and presentation glue. Public SDK consumers import the bundled facade
tpavanipradeepAGENTS.mdtpavanipradeep/everything-claude-code/.codex/AGENTS.md
development with 80%+ coverage - security-review — Comprehensive security checklist - coding-standards — Universal coding standards - frontend-patterns — React/Next.js patterns - frontend-slides — Viewport-safe HTML presentations and PPTX-to-web conversion - article
Clawdi-AIAGENTS.mdClawdi-AI/clawdi/AGENTS.md
docs/backend-development.md#verification`](docs/backend-development.md#verification). Done: `uv run pytest -q` exits 0 against that database. Frontend checks: ```bash bun run --cwd apps/web typecheck bun run --cwd apps/web test src/hosted/oss-clean.test.ts bunx biome
haruAGENTS.mdharu/redmine_ai_helper/AGENTS.md
Structure Patterns - Controllers: `app/controllers/ai_helper_*.rb` - Models: `app/models/ai_helper_*.rb` - Agents: `lib/redmine_ai_helper/agents/*_agent.rb` - Tools: `lib/redmine_ai_helper/tools/*_tools.rb` ### Frontend - HTML in ERB templates only — **never build HTML in JavaScript** (XSS prevention) - JavaScript: vanilla
weaviateAGENTS.mdweaviate/agent-skills/AGENTS.md
covers naive RAG tools, hierarchical RAG, vector DB memory, and Weaviate Query Agent. ### Optional Frontend Guide - [Frontend Interface](./skills/weaviate-cookbooks/references/frontend_interface.md): Build a Next.js frontend (App Router, Tailwind v4, shadcn/ui) to interact
Microsoft AzureAGENTS.mdAzure/gpt-rag-orchestrator/AGENTS.md
cross-cutting telemetry and reusable helpers. - `src/schemas.py` and `contracts/`: API and cross-repository contracts. - `frontend/`: the optional React/Vite administration dashboard. - `scripts/`, `.azure/`, `azure.yaml`, `Dockerfile`, and `infra/`: deployment and operational assets
luqman-v1AGENTS.mdluqman-v1/9router-go/AGENTS.md
src/lib/db/` | `internal/db/` | SQLite database layer (using pure-Go `modernc.org/sqlite`). | | `src/app/` (Next.js React 19 Frontend) | `web/src/` | Dashboard UI: Built with **Svelte 5 + Vite 8**, embedded into the binary via `web/embed.go
magnus919AGENTS.mdmagnus919/agent-skills/AGENTS.md
teach judgment for a discipline: frameworks, decision models, ownership boundaries, and process (`backend-engineering`, `frontend-engineering`, `data-engineering`, `platform-engineering`, `ml-engineering`, `qa-methodology`, `site-reliability-engineering`, `release-engineering
sirsjgAGENTS.mdsirsjg/flux/AGENTS.md
packages/ ├── cli/ # CLI tool - core, standalone ├── shared/ # Core types and storage abstraction ├── web/ # Preact frontend (optional dashboard) ├── server/ # Multi-repo aggregator (optional) └── mcp/ # MCP server for LLM integration ``` **Key architectural
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.
