How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
NousResearchAGENTS.mdNousResearch/hermes-agent/AGENTS.md
order: extend existing code → CLI command + skill → service-gated tool (`check_fn`) → plugin → MCP server in the catalog → new core tool (last resort). See the Footprint Ladder. - **Extend
NousResearchAGENTS.mdNousResearch/hermes-agent/hermes_cli/AGENTS.md
which refuse a deleted or missing named profile, #94590). Process-global per-profile slots (MCP discovery in `mcp_startup.py`, tool registry overlays) key on `hermes_constants.hermes_home_key()`, never a single flag
NousResearchAGENTS.mdNousResearch/hermes-agent/skills/AGENTS.md
description: (.*)$', text, re.M).group(1)) <= 60`. 2. **Prose references native Hermes tools or the MCP servers the skill expects, in backticks** (`terminal`, `web_extract`, `read_file`, `patch`, `search_files`, `vision
NousResearchAGENTS.mdNousResearch/hermes-agent/tools/AGENTS.md
MCP trust is a per-profile record:** `mcp_tool_registration.py:: _record_scope_trust` keys trust on the home; a secondary never adopts the launch profile's trust for a same-named server
affaan-mAGENTS.mdaffaan-m/ECC/AGENTS.md
Always-follow guidelines (common + per-language) scripts/ — Cross-platform Node.js utilities mcp-configs/ — 14 MCP server configurations tests/ — Test suite ``` `commands/` remains in the repo for compatibility, but the long
affaan-mAGENTS.mdaffaan-m/ECC/.codex/AGENTS.md
media — AI image/video/audio generation via fal.ai - dmux-workflows — Multi-agent orchestration with dmux ## MCP Servers Treat the project-local `.codex/config.toml` as the default Codex baseline for ECC. The current
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/AGENTS.md
runtime/ PTC execution sandbox/ process confinement deliverables/ turn deliverables fs/ filesystem access lsp/ language servers skill/ skill loading web/ search/fetch tools computer-use/ computer interaction browser-use/ browser interaction compaction
MicrosoftAGENTS.mdmicrosoft/vscode/extensions/copilot/assets/prompts/skills/agent-customization/references/agents.md
configuration and, when applicable, the parent agent. ## Tools Sources: built-in aliases, specific tools, MCP servers (` /*`), extension tools. **Special**: `[]` = no tools, omit = defaults. Body reference: `#tool: ` ### Tool Aliases | Alias | Purpose
MicrosoftAGENTS.mdmicrosoft/vscode/extensions/copilot/src/extension/chatSessions/copilotcli/AGENTS.md
shell, MCP) │ │ - Provides session persistence as events.jsonl files │ │ - Supports fleet mode and plan mode │ └─────────────────────────────────────────────────────────────────┘ │ ▼ ┌─────────────────────────────────────────────────────────────────┐ │ MCP Server (In-Process) │ │ (vscode-node/contribution.ts, vscode-node/inProcHttpServer.ts) │ │ - Provides VS Code-specific tools
MicrosoftAGENTS.mdmicrosoft/vscode/src/vs/platform/agentHost/AGENTS.md
# Multi-Chat Architecture > Node runtime service construction is documented separately in [`node/serviceBootstrapping.md`](node/serviceBootstrapping.md). > Host
MicrosoftAGENTS.mdmicrosoft/vscode/src/vs/platform/agentHost/node/copilot/prompts/AGENTS.md
openBrowserPage`, `runTask`, `getTaskOutput`) — NOT the extension's snake_case ids, and NOT shell / server-SDK / MCP tools (MCP is discovered dynamically and isn't in the launch snapshot). A line
LangChainAGENTS.mdlangchain-ai/langchain/AGENTS.md
install and use file search tools for best results. If needed, use the docs MCP server as defined in `.mcp.json` for programmatic access. - **Contributing Guide:** [Contributing Guide](https://docs.langchain.com/oss/python/contributing/overview)
VercelAGENTS.mdvercel/next.js/AGENTS.md
force webpack: ```bash next build --webpack # Production build with webpack next dev --webpack # Dev server with webpack ``` There is no `--no-turbopack` flag. ## Testing ```bash # Run specific test file (development
OpenAIAGENTS.mdopenai/codex/AGENTS.md
elsewhere. The exception is app-server API documentation, which is covered by the app-server guidance below. - Prefer private modules and explicitly exported public crate API. - If you change `ConfigToml
JuliusBrusseeAGENTS.mdJuliusBrussee/caveman/mcp/AGENTS.md
mcp — the Caveman MCP server (commercial Go core + MIT launcher) A thin **stdio JSON-RPC** adapter exposing the compression [engine](../engine/CLAUDE.md) as five MCP tools to any host (Claude Code
JuliusBrusseeAGENTS.mdJuliusBrussee/caveman/mem/AGENTS.md
bm25.go` — deterministic tokenizer + BM25 scorer (non-negative scores, so the threshold is meaningful). - `cmd/cavemem/` — MCP server + `remember`/`recall`/`supersede`/`history`/`forget` CLI subcommands (JSON). - `js/` + `py/` — thin TS and Python
JuliusBrusseeAGENTS.mdJuliusBrussee/caveman/proxy/AGENTS.md
silent no-op. `CAVE_SSRF_ALLOWLIST` opts loopback/private hosts back in (local model servers like Ollama; `localhost` as an entry covers 127.0.0.0/8 + ::1); metadata/link-local stay blocked in every mode
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.
