numpi

numpi is a skill for Claude Code, Codex from RudrenduPaul/skillguard. It costs 85 tokens per session (217 once invoked), scanned A, original, Apache-2.0.

A deliberately misspelled test skill named "numpi," which resembles the well-known Python package "numpy." It is included as an example of typosquatting, where a name is changed slightly to look trusted.

In plain words
What is it for?
Use it only in SkillGuard end-to-end tests for detecting typosquatting findings.
Why use it?
It helps verify that SkillGuard detects suspicious skill names that could trick users into installing the wrong add-on.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it only in SkillGuard end-to-end tests for detecting typosquatting findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rudrendupaul/skillguard/typosquat-skill
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.

Any agent
npx skills add RudrenduPaul/skillguard --skill typosquat-skill
Clone the repo
git clone --depth 1 https://github.com/RudrenduPaul/skillguard

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for numpi

README.md
[![agentmods](https://agentmods.dev/badge/skills/rudrendupaul/skillguard/typosquat-skill/github.svg)](https://agentmods.dev/skills/rudrendupaul/skillguard/typosquat-skill)
Your own site
<a href="https://agentmods.dev/skills/rudrendupaul/skillguard/typosquat-skill"><img src="https://agentmods.dev/badge/skills/rudrendupaul/skillguard/typosquat-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for numpi

Your own site · 80×15
<a href="https://agentmods.dev/skills/rudrendupaul/skillguard/typosquat-skill"><img src="https://agentmods.dev/badge/skills/rudrendupaul/skillguard/typosquat-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 217 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00085 $0.00217
Opus 5 $0.00043 $0.00109
Sonnet 5 $0.00017 $0.00043
Haiku 4.5 $0.00009 $0.00022

Measured 10d ago against content hash 73e70cd4634a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

numpi 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (hooks/greet.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

examples/typosquat-skill/SKILL.md · 28 lines

What it actually says

Typosquat Skill (fixture)

This skill exists only to trip SG10. Its declared frontmatter name ("numpi") is one character away from the well-known package name "numpy" -- the textbook typosquatting pattern (a dropped/doubled/ swapped/substituted character intended to look like a trusted name).

Run:

npx skillguard-cli scan ./examples/typosquat-skill

to see SkillGuard flag it with a HIGH-severity SG10 finding.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 28 lines · 85 tokens per session scan A 73e70cd4634a

Subscribe to this mod's changes

numpi is a skill published in the GitHub repository RudrenduPaul/skillguard (1 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 217 once invoked, about $0.0004 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.