slackdump
rusq/slackdump/AGENTS.md
compatible archives, build SQLite-backed archives, resume previous runs, search archives, run a local MCP server, and render archives in a built-in browser viewer or as static HTML. - Repository
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
rusq/slackdump/AGENTS.md
compatible archives, build SQLite-backed archives, resume previous runs, search archives, run a local MCP server, and render archives in a built-in browser viewer or as static HTML. - Repository
jgravelle/jcodemunch-mcp/AGENTS.md
repo retrieval weights from the ranking ledger ## Model-Driven Tool Tiering Your jcodemunch-mcp server narrows the exposed tool list based on the model you are running as. To avoid
runkids/skillshare/AGENTS.md
with a React dashboard and a Docusaurus documentation site. It synchronizes skills, agents, extras, MCP servers, and plugins across AI coding tools. This file contains only rules needed for every
NVIDIA/NeMo-Agent-Toolkit/AGENTS.md
selection, and output interpretation. - `skills/nat-telemetry/` - Logging, tracing, profiling, OpenTelemetry, and telemetry exporters. - `skills/nat-mcp-and-serving/` - MCP clients and servers, FastAPI, and workflow serving. - `skills/nat-path-checks/` - Documentation path-check failures, Markdown escaping, and slash
crbnos/carbon/AGENTS.md
policies and RLS helpers (authz manifest) | `.claude/rules/authz-manifest.md` | | Working with the database package | `packages/database/AGENTS.md` | | **Server & Services** | | | Writing service functions | `.claude/rules/conventions-services.md` | | Authentication, RBAC, permissions | `.claude/rules/authentication-system.md` + `packages/auth/AGENTS.md` | | Background jobs and events (Inngest) | `.claude/rules/event-system.md
expo/skills/AGENTS.md
plugin manifest .grok-plugin/ plugin.json # Grok Build plugin manifest .mcp.json # Claude Code and Codex MCP server configuration mcp.json # Cursor MCP server configuration skills/ README.md # Grouped index of all skills skill
felinics/Memoh/AGENTS.md
desktop client is a separate distribution boundary for Memoh Cloud or a hosted Memoh server. `apps/desktop` reuses `@memohai/web` modules, but owns the Electron shell, system tray behavior, menus, preload
samanhappy/mcphub/AGENTS.md
MCPHub — Agent Guide MCPHub (`@samanhappy/mcphub`) is a TypeScript/Node.js ESM hub that aggregates MCP servers behind a single HTTP service with a React/Vite dashboard. ## Always apply - Use `pnpm` (`pnpm@10.12.4`, declared
vercel/chat/apps/docs/AGENTS.md
concatenated `createLlmsRoute` output. `llms-full.txt` serves the concatenated corpus. - `/.well-known/mcp.json` intentionally returns 404; no MCP server is configured for this site. - `/sitemap.xml` is served by an external rewrite in `next.config.ts
numman-ali/cc-mirror/AGENTS.md
settings.json # Env overrides (API keys, base URLs, model defaults) │ ├── .claude.json # API-key approvals + onboarding/theme + MCP servers ├── tweakcc/ │ ├── config.json # Brand preset + theme list + toolsets │ └── system-prompts/ # Prompt-pack overlays (after tweakcc
jwadow/kiro-gateway/AGENTS.md
License**: AGPL-3.0 - **Main Entry Point**: `main.py` - **Package**: `kiro/` directory ## Essential Commands ### Running the Server ```bash # Default (host: 0.0.0.0, port: 8000) python main.py # Custom port python main.py --port 9000 # Custom
MCPJam/inspector/mcpjam-inspector/AGENTS.md
rewrites are allowed when they are needed to remove brittle fixture assumptions and isolate MCP server behavior
AmoyLab/Unla/agents.md
mcp-gateway`: The core data-plane gateway service. It routes client requests to MCP Servers or RESTful APIs. Think of it as the “Nginx” of the MCP domain. 2. `apiserver
777genius/agent-teams-ai/landing/AGENTS.md
config is fixed, use only the official Chrome DevTools MCP isolated stdio client as the temporary fallback. The current server uses newline-delimited JSON-RPC over stdio. Kill the spawned
Dicklesworthstone/mcp_agent_mail/AGENTS.md
only --include-bodies` - Product-wide thread summarization: - `mcp-agent-mail products summarize-thread MyProduct "br-123" --per-thread-limit 100 --no-llm` Server tools (for orchestrators) - `ensure_product(product
vibheksoni/stealth-browser-mcp/AGENTS.md
code, logs, errors, or commit messages. - Do not print to `stdout` from server runtime paths used by MCP `stdio`. - Use `apply_patch` for manual file edits. ## Security - Default transport
alpic-ai/skybridge/AGENTS.md
MCP Apps — interactive React views that render inside AI conversations. The core loop: an MCP server exposes tools. When the host (ChatGPT, Claude, VSCode…) calls a tool, the server returns
Lumiwealth/lumibot/AGENTS.md
calls a nonexistent or hallucinated method, fix the owned strategy through the authenticated BotSpot MCP server. Never add the invented method to LumiBot merely to make that strategy run. - Instructions
LetsFG/LetsFG/AGENTS.md
even hundreds of them — you want **Programmatic Flight Search (PFS)**: connect LetsFG as an MCP server at `https://letsfg.co/developers/api/mcp`, approve it (the consent at <https://letsfg.co/connect
rynfar/meridian/docs/agents.md
# Agent Setup This guide covers Claude client setup. For the Antigravity preview, use the
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.