What is AgentSpawnMCP AGENTS.md?

A set of instructions for AI coding agents working on AgentSpawnMCP, a server that connects compatible language models through web APIs.

Use it when developing AgentSpawnMCP, spawning tasks through another model provider, or working with its chat, vision, files, search, image, and agent features.

It explains the repository layout, supported operating modes, and provider-portability rules so an agent can change the project consistently.

How sandsaber/AgentSpawnMCP configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sandsaber/AgentSpawnMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sandsaber/AgentSpawnMCP/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sandsaber/AgentSpawnMCP

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sandsaber/agentspawnmcp/agents-md/github.svg)](https://agentmods.dev/instructions/sandsaber/agentspawnmcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sandsaber/agentspawnmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandsaber/agentspawnmcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sandsaber/agentspawnmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandsaber/agentspawnmcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,292 This file is loaded in full into every session.

When invoked 2,292 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02292	$0.02292
Opus 5.5	$0.00917	$0.00917
Sonnet 5.5	$0.00458	$0.00458
Haiku 4.5	$0.00229	$0.00229

Measured 2mo ago against content hash c48674830d20, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AgentSpawnMCP AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentSpawnMCP - Developer Guide

AgentSpawnMCP is a universal MCP server for OpenAI-compatible and Anthropic-compatible LLM HTTP APIs. It is built on FastMCP and plain httpx. Do not add provider SDKs unless the project explicitly changes direction.

The core design goal is provider portability: new providers should usually be configuration, CLI arguments, or small request-shape changes, not new client stacks.

Operating Modes

1. Spawn Agents MCP server (recommended integration path)

Runs from an installed package or directly through uvx. It exposes one provider-specific agent tool plus agent_info.

uvx agent-spawn-mcp spawn \
  --name minimax \
  --url https://api.minimax.io/anthropic/v1 \
  --token-env MINIMAX_TOKEN \
  --model MiniMax-M2.7 \
  --api-type anthropic

Use this mode for Claude Code, OpenCode, Codex MCP, and other MCP clients when the user only needs to delegate tasks to a single external model/provider.

2. Full MCP server

Runs from a cloned checkout and registers the full tool set: chat, stateful chat, vision, files, search, image generation, provider info, and agent tools.

git clone https://github.com/sandsaber/AgentSpawnMCP
cd AgentSpawnMCP
uv sync
uv run python main.py main --provider grok

Use this mode when the user needs the configured provider catalog and the general-purpose MCP tools.

Repository Map

main.py                         # Thin CLI shim to agent_spawn_mcp.__main__:app
agent_spawn_mcp/__main__.py                 # Typer CLI: main and spawn commands
agent_spawn_mcp/server.py                   # create_server() for the full server
agent_spawn_mcp/utils.py                    # Local chat history helpers
agent_spawn_mcp/config/models.py            # Pydantic config models and BUILTIN_PROVIDERS
agent_spawn_mcp/config/loader.py            # load_config(), active provider globals
agent_spawn_mcp/providers/base.py           # Base provider shape
agent_spawn_mcp/providers/openai_compat.py  # HTTP client for OpenAI/Anthropic-style APIs
agent_spawn_mcp/tools/                      # Full server MCP tool registration modules
agent_spawn_mcp/agent_spawn/server.py       # create_agent_spawn_server()
agent_spawn_mcp/agent_spawn/tools/base.py   # _create_agent_tool() factory
agent_spawn_mcp/agent_spawn/tools/registry.py
configs/default.yaml            # Default full-server provider catalog
tests/                          # Request-shape and URL-construction tests

Read the full file on GitHub · 277 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 277 lines · 2,292 tokens per session scan A c48674830d20

Subscribe to this mod's changes

AgentSpawnMCP AGENTS.md is an instructions file published in the GitHub repository sandsaber/AgentSpawnMCP (0 stars, last pushed 5mo ago), licensed MIT. It adds 2,292 tokens to every session, about $0.0092 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

AgentSpawnMCP AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
AgentSpawnMCP AGENTS.mdsandsaber/AgentSpawnMCP	Instructions file	0	5mo ago	MIT	A	2,292	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

AgentSpawnMCP: Instructions file for Codex