socket-inspect

A package-safety research workflow using Socket, a service that checks software dependencies for security and supply-chain risks. It gathers package scores, alerts, malware findings, CVEs, patches, and alternative-package information.

In plain words
What is it for?
Use it to investigate flagged packages, malware concerns, known vulnerabilities, maintenance signals, supply-chain risks, possible replacements, and available Socket patches.
Why use it?
It helps you assess a dependency before installing, keeping, or replacing it instead of relying only on its name or popularity.

Skill for Claude CodeCodex

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 skills/socketdev/sauce/socket-inspect
Any agent
npx skills add SocketDev/sauce --skill socket-inspect
Clone the repo
git clone --depth 1 https://github.com/SocketDev/sauce

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,104 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00050 $0.03104
Opus 5 $0.00025 $0.01552
Sonnet 5 $0.00010 $0.00621
Haiku 4.5 $0.00005 $0.00310

Measured yesterday against content hash c9144b14df1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

socket-inspect scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

<details><summary>The curl call, its auth requirements, and every field to extract</summary>
skills/socket-inspect/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Inspect

Research a package before you depend on it. This skill pulls every available signal from Socket - scores, alerts, malware verdicts, CVEs, and supply-chain risk indicators - checks the socket.dev package page for additional context, evaluates alternatives when warranted, and surfaces available Socket patches. Use it to make an informed decision before adding, keeping, or replacing any dependency.

When to Use

  • Evaluate a package before installing it
  • Investigate a flagged dependency from a scan
  • Check the security, quality, or maintenance status of a package
  • Compare alternatives for a dependency choice
  • Check if a package is malware
  • Check if Socket has patches available for a vulnerable package
  • Get a comprehensive supply-chain risk report

Prerequisites

Socket CLI Setup

Use pnpm dlx socket to run the Socket CLI - this always fetches the latest version and requires no global install. Verify it works:

pnpm dlx socket --version

All commands in this skill use the pnpm dlx socket prefix (e.g., pnpm dlx socket scan create ...).

Optional global install: If you prefer a global socket command, install with npm install -g socket@latest (must be version 1.0.0 or higher).

Authentication

For users without a Socket account: Configure the public demo token directly:

pnpm dlx socket config set apiToken sktsec_t_--RAN5U4ivauy4w37-6aoKyYPDt5ZbaT5JBVMqiwKo_api --no-banner --no-spinner
pnpm dlx socket config set defaultOrg SocketDemo --no-banner --no-spinner

This provides limited access to CLI features like pnpm dlx socket fix, pnpm dlx socket package score, sfw, and socket-patch with rate limits. No account creation is needed for basic usage. Note: The public demo token cannot create scans (pnpm dlx socket scan create requires the full-scans:create permission). For scanning and full-rate access, create a free account at https://socket.dev.

Read the full file on GitHub · 298 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 · 298 lines · 50 tokens per session scan A c9144b14df1e

Subscribe to this mod's changes

socket-inspect is a skill published in the GitHub repository SocketDev/sauce (2 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 3,104 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens