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/baiehclaca/service/agents-mdgit clone --depth 1 https://github.com/baiehclaca/serviceWrote 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/baiehclaca/service/agents-md)<a href="https://agentmods.dev/instructions/baiehclaca/service/agents-md"><img src="https://agentmods.dev/badge/instructions/baiehclaca/service/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 | $0.01065 | $0.01065 |
| Opus 5 | $0.00532 | $0.00532 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
service AGENTS.md scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Check the MCP server: `curl http://localhost:3333/mcp` How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SERVICE — MCP Hub & Notification Center
Mission Overview
SERVICE is a 24/7 CLI daemon and MCP server hub. It is the only MCP server an AI agent needs to connect to. It:
- Aggregates any number of downstream MCP servers (proxying all their tools under one roof)
- Acts as a real-time notification gateway — pushing platform events (X, email, Slack, WhatsApp, phone, custom) to connected AI agents
- Exposes a CLI for human operators to configure integrations, view the live notification feed, and manage connected agents
- Allows any new integration to be registered via a config/UI without rebuilding
Tech Stack
- Runtime: Node.js v25.8.2, TypeScript, Bun for scripts
- MCP SDK:
@modelcontextprotocol/sdk(Streamable HTTP + stdio transports) - Database: SQLite (better-sqlite3) for persistence — integrations, notifications, agent sessions
- CLI: ink (React for CLI) or commander + ora for interactive terminal UI
- Process management: Self-daemonizing with PID file, auto-restart
- Notifications: SSE to connected agents, WebSocket fallback
Architecture
AI Agent (Claude/Cursor/etc.)
│ stdio or HTTP MCP connection
▼
┌─────────────────────────────────┐
│ SERVICE daemon │
│ ┌──────────────────────────┐ │
│ │ MCP Hub (aggregator) │ │ ← Proxies tools from all connected MCPs
│ │ Tool Router │ │
│ └──────────────────────────┘ │
│ ┌──────────────────────────┐ │
│ │ Notification Gateway │ │ ← 24/7 event listener, pushes to agents
│ │ Integration Manager │ │
│ └──────────────────────────┘ │
│ ┌──────────────────────────┐ │
│ │ CLI Dashboard │ │ ← Human operator interface
│ └──────────────────────────┘ │
└─────────────────────────────────┘
│ │
┌────┘ └────────────┐
▼ ▼
Downstream MCPs External Platforms
(filesystem, github, (X/Twitter, Email, Slack,
memory, brave, etc.) WhatsApp, Phone, custom)
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.
- 3d ago First seen · 118 lines · 1,065 tokens per session scan A af0eb96ef9f8
service AGENTS.md is an instructions file published in the GitHub repository baiehclaca/service (1 stars, last pushed 5mo ago), licensed MIT. It adds 1,065 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
droidproxy AGENTS.md
AGENTS.md instructions for nikships/droidproxy, covering agents.md, build & run, cli-proxy-api are stopped before the new app starts, debug build (no .app bundle, no relaunch) and build the .app bundle first, then open it.
ox AGENTS.md
AGENTS.md instructions for sageox/ox, covering human attention is the scarcest resource, what is ox?, quick start, terminology and required reviews.
zentty AGENTS.md
AGENTS.md instructions for dedene/zentty, covering agents.md, testing, design docs, project generation and agent bench.
zentty CLAUDE.md
Claude Code instructions for dedene/zentty, a project described as: A native macOS terminal for agent-driven development, built on Ghostty.
hermes-droid AGENTS.md
Instructions for magnus919/hermes-droid, covering agents.md, purpose, before editing, conventions and validation.
tokenboard CLAUDE.md
Instructions for angelafeliciaa/tokenboard, covering tokenboard — repo instructions, no personal identifiers in docs/code (mandatory) and rules (mandatory).