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/novuhq/skills/agents-mdgit clone --depth 1 https://github.com/novuhq/skillsWrote 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/novuhq/skills/agents-md)<a href="https://agentmods.dev/instructions/novuhq/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/novuhq/skills/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 | $0.01470 | $0.01470 |
| Opus 5 | $0.00735 | $0.00735 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
skills 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Cursor, Codex, Copilot, etc.) when working with the Novu skills in this repository. It is auto-loaded as repo-wide context and is not itself a discoverable skill.
Repository Overview
Novu is a notification infrastructure platform for sending notifications across email, SMS, push, chat, and in-app channels. Workflows can be created via the Novu dashboard UI or in code using @novu/framework.
This repository ships eight discrete agent skills under skills/. Each is registered independently by every spec-compliant loader.
Sub-Skills
| Skill | Use When... |
|---|---|
novu-design-workflow |
Designing or planning a new workflow; choosing channels, severity, critical, digest behavior; matching a use case to a template |
novu-dashboard-workflows |
Authoring step content (subject, body, editorType, headers, conditions) on workflows defined in the Novu Dashboard or via the Novu MCP |
novu-trigger-notification |
Sending notifications, triggering workflows, single or bulk sends |
novu-manage-subscribers |
Creating, updating, listing, or deleting subscribers; managing topics and groups |
novu-inbox-integration |
Adding the in-app notification inbox, bell icon, or notification feed to a web app and react native app |
novu-manage-preferences |
Setting up subscriber notification preferences, workflow defaults, or the Preferences UI |
novu-framework-integration |
Defining notification workflows in code with @novu/framework (Bridge Endpoint, steps, controls, React Email, deployment) |
novu-connect-agent |
Creating a Novu managed agent and connecting a channel (Slack, email, Telegram, WhatsApp, MS Teams) via npx novu@latest connect |
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 · 105 lines · 1,470 tokens per session scan A 3d929c3077ef
skills AGENTS.md is an instructions file published in the GitHub repository novuhq/skills (3 stars, last pushed today), licensed MIT. It adds 1,470 tokens to every session, about $0.0073 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
novu AGENTS.md
AGENTS.md instructions for novuhq/novu, covering agents.md, cursor cloud specific instructions, build, ai boundaries and always.
ntfy-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/ntfy-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
agent-toast CLAUDE.md
Claude Code instructions for hopoduck/agent-toast, covering claude.md, requirements, build & dev commands, lint & format (workspace root) and rust (workspace).
agent-inbox CLAUDE.md
Claude Code instructions for Ideaplaces/agent-inbox, covering agent inbox: working notes, local development, gotchas already paid for, keep readme.md current and conventions.
agent-setup AGENTS.md
Instructions for DefaultPerson/agent-setup, covering core, code edits, validation, priorities and if uncertain.
n-cli AGENTS.md
Instructions for lba-studio/n-cli, covering agents, project overview, folder structure, examples and releasing a new version.