What is slop-mcp AGENTS.md?

Repository instructions for slop-mcp, an MCP coordinator that combines many MCP servers behind a smaller set of agent tools. They also document project commands for building, testing, formatting, and integration checks.

Use them when developing slop-mcp, running its Go tests and checks, or testing integrations with Claude, Gemini, or Copilot.

They explain the project’s token-saving approach and provide the commands needed to verify changes, including tests with real AI-agent command-line tools.

How standardbeagle/slop-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to standardbeagle/slop-mcp. 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/standardbeagle/slop-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/standardbeagle/slop-mcp

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/standardbeagle/slop-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/standardbeagle/slop-mcp/agents-md)

Your own site

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

Per session 1,934 This file is loaded in full into every session.

When invoked 1,934 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	$0.01934	$0.01934
Opus 5.5	$0.00774	$0.00774
Sonnet 5.5	$0.00387	$0.00387
Haiku 4.5	$0.00193	$0.00193

Measured 2mo ago against content hash cac2461b63d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

slop-mcp 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 · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

此檔示 Claude Code (claude.ai/code) 於此倉行事之準。

Project Philosophy

本案重客戶 token 成本；必用 progressive disclosure，一答即給精確所需。

Project Overview

slop-mcp，MCP orchestrator 也；聚多 MCP servers，而僅示 agents 8 meta-tools。解 context window bloat：非 50 MCPs × 20 tools = 1000 tool definitions，無論規模，agents 但見 8 tools。

Build & Development Commands

# Build
make build              # Build slop-mcp and memory-cli to ./build/
make install            # Build and install to ~/.local/bin

# Test
make test               # Unit tests (fast, no network)
make test-mock          # Integration tests with mock MCP (fast)
make test-integration   # Integration tests with real MCPs (slow, requires npx)

# Lint & Format
make lint               # go vet + golangci-lint
make fmt                # Format code
make tidy               # Tidy go.mod

Running a Single Test

go test -v -run TestHandleSearchTools ./internal/server/...

End-to-End Integration Tests

以真 AI agent CLIs（Claude, Gemini, Copilot）驗 slop-mcp：

# Run all integration tests (requires API keys configured)
./scripts/integration-test.sh

# Test specific agent
./scripts/integration-test.sh claude
./scripts/integration-test.sh gemini
./scripts/integration-test.sh copilot

# Via pre-commit (manual stage)
pre-commit run integration-test --hook-stage manual

# Verbose output
SLOP_TEST_VERBOSE=1 ./scripts/integration-test.sh

Requirements:

Built binary (make build first)
API keys configured for each CLI
CLIs installed: claude, gemini, copilot

Build Requirements

Go 1.25.0+ (required by go-sdk v1.6.1)
Build tags: -tags mcp_go_client_oauth（OAuth 必需）

Architecture

Package Structure

cmd/
├── slop-mcp/           # Main server binary (serve, run, mcp subcommands)
└── memory-cli/         # Persistent memory tool for agent sessions

internal/
├── server/             # MCP server, tool handlers, JSON schemas
├── registry/           # MCP connections, state tracking, tool search index
├── config/             # KDL config loading with three-tier scoping
├── cli/                # Local CLI tool registry (executed without MCP overhead)
└── auth/               # OAuth token storage and automatic refresh

Read the full file on GitHub · 218 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 · 218 lines · 1,934 tokens per session scan A cac2461b63d7

Subscribe to this mod's changes

slop-mcp AGENTS.md is an instructions file published in the GitHub repository standardbeagle/slop-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,934 tokens to every session, about $0.0077 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.

Go ai-agents context-window developer-tools llm-tools mcp

slop-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
slop-mcp AGENTS.mdstandardbeagle/slop-mcp	Instructions file	1	1mo ago	MIT	A	1,934	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	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	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

slop-mcp: Instructions file for Codex