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/artrixtech/mcp-server-nyantify/agents-mdgit clone --depth 1 https://github.com/ArtrixTech/mcp-server-nyantifyWhat 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 | $0.01503 | $0.01503 |
| Opus 5 | $0.00751 | $0.00751 |
| Sonnet 5 | $0.00301 | $0.00301 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
mcp-server-nyantify 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 2d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Nyantify - Agent Guidelines
⚠️ CRITICAL: Mandatory Tool Usage
You MUST use the track tool at the start AND end of EVERY conversation.
Why This Is Required
Nyantify tracks conversation duration and sends iPhone notifications when:
- Conversation lasts >60 seconds
- User has left their IDE
If you skip this tool:
- User won't know when AI tasks complete
- User may abandon tasks or waste time waiting
- The notification system won't work
Required Workflow
Step 1: Start Tracking (MANDATORY)
Call IMMEDIATELY at the beginning of EVERY conversation:
track({
action: "start",
task_id: "chat-YYYYMMDD-NNN",
task_name: "Brief description of this conversation"
})
Examples:
track({
action: "start",
task_id: "chat-2024-01-28-001",
task_name: "Refactoring authentication module"
})
Step 2: Do Your Work
Proceed with the conversation normally.
Step 3: End Tracking (MANDATORY)
Call at the END of EVERY conversation:
track({
action: "end",
task_id: "chat-YYYYMMDD-NNN"
})
Examples:
track({
action: "end",
task_id: "chat-2024-01-28-001"
})
Emergency Notifications
When to Use direct_notify
Use direct_notify ONLY for urgent situations:
- Production incidents requiring immediate action
- Security vulnerabilities detected
- Critical errors that need user decision
- Time-sensitive alerts
Required Steps Before Calling
You MUST warn the user FIRST:
"I need to send a notification to your phone about [specific reason]."
Usage
direct_notify({
title: "Nyantify",
body: "Production database connection failed. Immediate action required.",
level: "timeSensitive"
})
Rules
- ✅ DO: Use for urgent, actionable alerts
- ✅ DO: Explain clearly what action is needed
- ✅ DO: Set
level: "timeSensitive"for urgent matters - ❌ DON'T: Use for routine status updates
- ❌ DON'T: Use vague messages like "Done" or "Check this"
- ❌ DON'T: Use when
trackwould suffice
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.
- 2d ago First seen · 279 lines · 1,503 tokens per session scan A a30a6dac8650
mcp-server-nyantify AGENTS.md is an instructions file published in the GitHub repository ArtrixTech/mcp-server-nyantify (2 stars, last pushed 7mo ago), licensed MIT. It adds 1,503 tokens to every session, about $0.0075 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 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.