AGENTS.md examples from real projects

PrimeIntellect-aiAGENTS.md

prime-agent

PrimeIntellect-ai/prime-agent/AGENTS.md

prompts TOML rule map) followed by one dynamic tail (packages, project context, skills inventory, MCP servers, environment, session role); the harness digest stays a separate `[harness-digest]` user message. `prime

No other project uses it yet

handsontableReads credentialsAGENTS.md

handsontable

handsontable/handsontable/AGENTS.md

Angular, and Vue 3 wrappers. It runs entirely in the browser — frontend-only, no server-side logic. It cannot access the internet unless explicitly configured (air-gapped environment support). There

QwikDevAGENTS.md

qwik

QwikDev/qwik/AGENTS.md

repo. Use `~/.config/ruler/` for personal preferences, local workflow shortcuts, API keys, and personal MCP servers: ```bash ruler init --global ``` If it helps everyone working in this repo

QwikDevAGENTS.md

qwik

QwikDev/qwik/.ruler/AGENTS.md

generate them (once per worktree): > > ```bash > pnpm dlx @intellectronica/ruler@0.3.42 apply --no-gitignore --no-mcp > ``` > Canonical source for repo-wide AI coding agent rules. For contributor setup, see > [CONTRIBUTING.md](./CONTRIBUTING.md

GitHubAGENTS.md

docs / responsible-use

github/docs/content/copilot/responsible-use/agents.md

Copilot. The SDK communicates with Copilot CLI over JSON-RPC and supports custom agents, MCP server integrations, lifecycle hooks, and session management. * **The {% data variables.copilot.github_copilot_app %}**: A desktop application

PydanticAGENTS.md

pydantic-ai

pydantic/pydantic-ai/AGENTS.md

OTel instrumentation of Pydantic AI and `httpx` - If you have access to the Logfire MCP server, you can use it to inspect agent runs, tool calls, and model requests ## Test

PydanticReads credentialsAGENTS.md

pydantic-ai / pydantic_clai2

pydantic/pydantic-ai/src/pydantic_clai2/AGENTS.md

owns the host API, loading, and credential picker helpers. `builtin_plugins/` and `mcp/` retain their plugin and server boundaries. Move a capability to core or harness if it does

PydanticReads credentialsAGENTS.md

pydantic-ai / tests

pydantic/pydantic-ai/tests/AGENTS.md

without proper assertions or that verify opposite behavior create false positives - Test MCP against real `tests.mcp_server` instance, not mocks — extend test server with helper tools to expose runtime context

gofr-devReads credentialsAGENTS.md

gofr

gofr-dev/gofr/docs/AGENTS.md

gofr.dev/docs/advanced-guide/injecting-databases-drivers> - Calling LLMs (`app.AddLLM`, `c.LLM()`, env config, multiple models, embeddings): <https://gofr.dev/docs/advanced-guide/llm> - MCP server and agent loops (`app.EnableMCP`, `c.LLM().Tools()`): <https://gofr.dev/docs/advanced-guide/mcp> - Streaming responses (SSE / NDJSON, `response.Stream

JetBrainsAGENTS.md

intellij-community

JetBrains/intellij-community/AGENTS.md

Tools Search the repository with `./tools/accio.cmd`, not with the `search_*` tools of an IDE MCP server. It answers from the working tree of the current checkout, a lease included

kortix-aiReads credentialsAGENTS.md

suna

kortix-ai/suna/AGENTS.md

with `runtimeSupports`. pi lists `session.subagents`, `session.compact`, `session.commands` and `session.steer`. pi does not serve rewind, MCP servers, the todo list, shell turns, part edits or `session.attach`. The harness rules

refactoringhqDeletes or force-pushesAGENTS.md

tolaria

refactoringhq/tolaria/AGENTS.md

obtain repository-owner approval before pushing. **If CodeScene gate blocks your push:** use `mcp__codescene__code_health_score` to find the worst file, refactor it, commit, push again

teng-linAGENTS.md

notebooklm-py

teng-lin/notebooklm-py/AGENTS.md

Internal:** `_*.py` and `_*/` (`_app/`, `_auth/`, `_runtime/`, `_sources.py`, `_artifacts.py`). - **Adapters & Wire:** `cli/` (Click), `mcp/` (FastMCP), `server/` (FastAPI), `rpc/` (batchexecute RPC facade), `_android/` (gRPC session & codecs). - **Tests & Data:** `tests/unit/`, `tests/integration/` (VCR), `tests/server

No other project uses it yet

rocketride-orgAGENTS.md

rocketride-server

rocketride-org/rocketride-server/AGENTS.md

catalog) | | Test a node | `docs/development/nodes/testing.md` | | Client (SDK) docs | `docs/development/clients/readme-schema.md`; sources in `docs/public/ /` | | MCP surface | `docs/public/mcp/` | | Engine internals | `docs/development/engine/index.md` | | WebSocket (5565) protocol | `docs/public/product/connect/websocket/` | | Crash reporting / minidumps | `docs/development/engine/crash-reporting.md` | | Shell apps | `docs/public/product/guides/apps/index.md

storytoldAGENTS.md

pdfcraft

storytold/pdfcraft/AGENTS.md

Never enable it by default, widen the bind address, or log the token. - **The MCP server is opt-in.** Never make the app, the CLI or an installer start

agent0aiAGENTS.md

agent-zero / prompts

agent0ai/agent-zero/prompts/AGENTS.md

together with the capability; non-tool system fragments stay capability-neutral. - MCP prompt templates own the static outer, server, and tool framing; `helpers/mcp_handler.py` supplies policy-filtered names, descriptions, and schemas

nukeopAGENTS.md

nuclear

nukeop/nuclear/AGENTS.md

respond` command). - `http_api/` - Axum REST + SSE server for Nuclear Jam remote control - `mcp/` - MCP server exposing player functions as tools to LLM clients - `mpd/` - MPD-protocol TCP server

langbot-appReads credentialsAGENTS.md

LangBot

langbot-app/LangBot/AGENTS.md

running but the current user lacks Docker socket permission. - Do not confuse external MCP servers LangBot connects to (`pkg/provider/tools/loaders/mcp.py`) with LangBot's own `/mcp` server (`pkg/api/mcp/`). ## Principles - Keep it simple

xerj-orgPipes a download into a shellAGENTS.md

xerj

xerj-org/xerj/AGENTS.md

readable capability reference + honest caveats | https://xerj.org/llms.txt · https://xerj.org/llms-full.txt | | MCP tool schemas (generated from the server, drift-gated) | [landing/docs/agents/schemas/mcp-tools.json](./landing/docs/agents/schemas/mcp-tools.json) · source: [engine/crates/xerj-mcp/](./engine/crates/xerj-mcp/) | | Verified how-to guides | [docs/recipes

No other project uses it yet

tusen-aiAGENTS.md

naive-ui

tusen-ai/naive-ui/AGENTS.md

user-facing behavior unless requested. ## Build and Development Commands ```bash # Start documentation site dev server pnpm run dev # Run all unit tests pnpm run test # Run tests for a specific

No other project uses it yet