Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/waylaidwanderer/background-process-mcp/agents-mdgit clone --depth 1 https://github.com/waylaidwanderer/background-process-mcpWrote 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.
[](https://agentmods.dev/instructions/waylaidwanderer/background-process-mcp/agents-md)<a href="https://agentmods.dev/instructions/waylaidwanderer/background-process-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/waylaidwanderer/background-process-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01001 | $0.01001 |
| Opus 5 | $0.00500 | $0.00500 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
background-process-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Architecture: Background Process MCP
This document defines the core architectural principles for this project. All development must adhere to these principles to ensure a robust, maintainable, and consistent system.
1. Core Principle: Server-Centric, Single Source of Truth
The entire system is built on a strict server-centric model. The Core Service is the absolute and only source of truth for all state within the application. Clients are considered "dumb" renderers of this state.
DO NOT store any persistent state on the clients (TUI, MCP). A client should be able to disconnect and reconnect at any time and be brought back to the correct state entirely by the server.
2. Component Responsibilities
2.1. The Core Service (ProcessManager & WebSocketServer)
The Core Service is the brain and the state machine.
- Single Source of Truth: It exclusively owns and manages all process state, including:
- The list of all running and stopped processes.
- The Process ID (
processId), command, PID, and status of each process. - The complete, capped output history for every process.
- Lifecycle Management: It is solely responsible for spawning (
node-pty), terminating (tree-kill), and cleaning up child processes. - Business Logic: It enforces all system rules, such as the concurrent process limit.
- Data Transformation: It is responsible for preparing data for consumers (e.g., stripping ANSI codes for the MCP client).
- Communication Hub: It manages the WebSocket server, broadcasting state changes to all connected clients and responding to direct requests.
2.2. The Clients (TUI & MCP)
Clients are stateless views and command issuers.
- Stateless: Clients MUST NOT store their own long-term state, especially output history. They should render the state provided by the server.
- View Rendering: Their primary responsibility is to present the server's state to the user or the LLM. The TUI renders a visual dashboard; the MCP client formats data for the LLM.
- Command Issuers: They translate user/LLM input into well-formed command messages (e.g.,
client.start_process) and send them to the Core Service.
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.
- 5d ago First seen · 100 lines · 1,001 tokens per session scan A 3f7089e57b99
background-process-mcp AGENTS.md is an instructions file published in the GitHub repository waylaidwanderer/background-process-mcp (11 stars, last pushed 10mo ago), licensed MIT. It adds 1,001 tokens to every session, about $0.0050 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).