smol-cli

A set of project rules for using sped-cli, a command-line tool with shortcuts for common development commands. It also requires reading the project’s instruction files before running commands.

In plain words
What is it for?
Use it to initialize sped-cli, run its aliases for Git, package installation, frameworks, files, development servers, builds, and linting.
Why use it?
It standardizes setup and command usage across the project and prevents instruction files from being removed or changed accidentally.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/electroo69/sped-cli/smol-cli
Clone the repo
git clone --depth 1 https://github.com/electroo69/sped-cli

Made for: Cursor.

Per session 1,947 This file is loaded in full into every session.
When invoked 1,947 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01947 $0.01947
Opus 5 $0.00974 $0.00974
Sonnet 5 $0.00389 $0.00389
Haiku 4.5 $0.00195 $0.00195

Measured yesterday against content hash 3ba3312f86ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smol-cli 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 yesterday.

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.

skills/.cursor/rules/smol-cli.mdc · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY: sped-cli Shell Rules

Setup once per project: install with npm i -g @electrooo69/sped-cli@latest --force, then run sped setup --all in the project root if .sped-cli/ is missing. Never delete .sped-cli/. Only follow the instruction file for your current agent. Do not delete or modify other agents' instruction files unless explicitly asked. Read the entire .sped-cli/DOCS.md and .sped-cli/aliases.json files before using shell commands. Use sped-cli aliases whenever available (gs, ni, nxa, etc.). If an alias is unavailable, expand it manually and include a short comment noting which alias you expanded. Never silently use long-form commands.

Most Used Aliases (memorize these)

Git Packages Frameworks Files
gs status ni npm install nxa create next h head
ga add all nid install pkg via create vite t tail
gc commit nidd install -D nga create angular l cat -n
gp push dev start dev sva create svelte sf find
gpl pull b build vua create vue sg grep
gcb new branch lint linter nua create nuxt todo TODOs
gl log tu unit tests rma create remix lt tree
gd diff check all checks t3a create t3 rg ripgrep

Framework Workflows

# Next.js:     nxa my-app → ni → dev
# Vite:        via my-app → ni → dev
# Angular:     nga my-app → ni → ngs
# Supabase:    sbi → sbs → sbm add_users → sbp → sbt
# Prisma:      pri → prm init → prg → prs
# Git:         gs → ga → gc "msg" → gp
# Testing:     vit (vitest) · pwr (playwright) · tu (unit)
# TypeScript:  tsc · tscw (watch) · tscn (noEmit)
# Linting:     esl · eslf (fix) · bml (biome) · prt (prettier)

Full Reference (324 commands)

For the complete alias list, read .sped-cli/aliases.json.

Below is a summary by category. For exact expansions, always check .sped-cli/aliases.json.

File Ops (20): h t l v e w a x i d cp mv cat touch wc sz ch ln hd md5

Read the full file on GitHub · 80 lines

Changes

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.

  1. yesterday First seen · 80 lines · 1,947 tokens per session scan A 3ba3312f86ac

Subscribe to this mod's changes

smol-cli is a cursor rule published in the GitHub repository electroo69/sped-cli (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,947 tokens to every session, about $0.0097 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.