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/lba-studio/n-cli/agents-mdgit clone --depth 1 https://github.com/lba-studio/n-cliWhat 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 | $0.00781 | $0.00781 |
| Opus 5 | $0.00391 | $0.00391 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
n-cli 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
If a .cursor/rules directory or file exists in this repository, read and follow the rules defined there.
Maintenance: When adding new commands or subcommands, update both AGENTS.md and README.md to reflect the change.
Project Overview
n-cli is a notification CLI tool that lets you send notifications to yourself (desktop, Discord, Slack, custom webhooks) from the command line. A primary use case is getting notified when long-running commands or LLM coding agents finish.
For the full list of commands and configuration options, see README.md.
Folder Structure
cmd/ # Cobra command definitions — one file per top-level command
setup/ # Subcommands for agent integrations (Cursor, Codex, Claude Code)
hook/ # Subcommands for processing LLM agent hook events (Cursor, Codex, Claude Code)
where/ # Subcommands for the `where` command
internal/
config/ # Config loading and initialisation (viper-based, ~/.n-cli/config.yaml)
pkg/
notifier/ # Core notification logic — each channel (Discord, Slack, customs, system) has its own file
marker/ # Tracks command run metrics (duration, exit code) for `n-cli run`
webhook/ # Shared HTTP webhook utilities
formatter/ # Message formatting helpers
monitor/ # Process monitoring utilities
Examples
Adding a new notification channel (e.g. Telegram): add a telegram.go in pkg/notifier/, implement the Notifier interface, and wire it up in pkg/notifier/notify.go alongside the existing channels. Add its config struct to internal/config.
Adding a new top-level command: create cmd/cmd_<name>.go, define a New<Name>Cmd() *cobra.Command function, and register it in cmd/root.go's init().
Adding a new setup subcommand (e.g. for a new agent integration): add a file in cmd/setup/, implement the setup logic there, and register it in cmd/cmd_setup.go's NewSetupCmd().
Adding a new hook subcommand (e.g. for a new agent integration): add a file in cmd/hook/, implement the hook handler there, and register it in cmd/cmd_hook.go's NewHookCmd().
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 · 59 lines · 781 tokens per session scan A d15bdc01d51c
n-cli AGENTS.md is an instructions file published in the GitHub repository lba-studio/n-cli (5 stars, last pushed 2mo ago), licensed MIT. It adds 781 tokens to every session, about $0.0039 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
chat AGENTS.md
Instructions for vercel/chat, covering agents.md, commands, per-package, monorepo layout and architecture.
chat CLAUDE.md
Instructions for vercel/chat, a project described as: A unified TypeScript SDK for building chat bots across Slack, Microsoft Teams, Google Chat, Discord, and more.
kimaki AGENTS.md
Instructions for remorses/kimaki, covering repo architecture, gateway-proxy (rust), gateway onboarding flow (gateway mode), db package and opencode sdk.
agentconnect CLAUDE.md
Instructions for agentconnect-md/agentconnect, covering claude.md, what this is, monorepo (pnpm workspace, packages/), platform modules and comment style.
personal-agent-template AGENTS.md
Instructions for vercel-labs/personal-agent-template, covering personal agent template, quick reference, structure, documentation and eve framework.
nexu AGENTS.md
Instructions for nexu-io/nexu, covering agents.md, repo overview, project overview, commands and branch model.