socket-setup

A setup guide for Socket, a tool that checks software dependencies and can protect or patch them. It covers installing the command-line tools, signing in, setting rules, and connecting Socket to code-hosting and CI systems.

In plain words
What is it for?
Use it to install Socket tools, authenticate, configure policies, set up Socket Firewall or socket-patch, and add Socket checks to CI/CD pipelines.
Why use it?
It turns the initial setup into a sequence of checks and configuration steps, including choosing the project's package manager and preparing tokens for automation.

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

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,261 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00047 $0.06261
Opus 5 $0.00023 $0.03130
Sonnet 5 $0.00009 $0.01252
Haiku 4.5 $0.00005 $0.00626

Measured yesterday against content hash ee8f28d2d8cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

socket-setup scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- **nvm** (recommended): `curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash` then `nvm install 20`

Makes network callslowCapability

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

- **nvm** (recommended): `curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash` then `nvm install 20`
skills/socket-setup/SKILL.md · 590 lines

How it starts

The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup

When to Use

  • User wants to get started with Socket
  • User needs to install/configure the Socket CLI
  • User wants to authenticate with Socket
  • User wants to set up Socket Firewall
  • User wants to set up socket-patch for automated patching
  • User wants to add Socket to CI/CD pipelines
  • User wants to configure Socket policies (socket.yml)
  • User wants to set up API tokens for CI or local development
  • User is having trouble authenticating
  • User wants to install Socket tools globally for local development
  • User wants to integrate Socket into Dockerfiles

Step 1: Check Prerequisites

Ask each tool for its version. A command not found error means the tool is not installed:

node --version
socket --version
sfw --version
socket-patch --version

Detect the package manager from the lock file in the project root - the command prints only the files that exist:

ls -d package-lock.json pnpm-lock.yaml yarn.lock bun.lock bun.lockb 2>/dev/null || true

package-lock.json means npm, pnpm-lock.yaml means pnpm, yarn.lock means yarn, and bun.lock or bun.lockb means bun. With no lock file, ask the user which package manager the project uses.

Handle results:

  • If node --version fails: prompt the user to install Node.js. Suggest:
    • nvm (recommended): curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash then nvm install 20
    • Homebrew (macOS): brew install node
    • Official installer: https://nodejs.org/
  • If node --version reports below v18: warn that Node.js 18+ is required and suggest upgrading
  • If socket --version reports below 1.0.0: warn that the Socket CLI is below 1.x and prompt to update with npm install -g socket@latest
  • If socket --version fails: proceed to Step 3 (Install the CLI)

Step 2: Ask About Socket Account

Ask the user whether they have or want to create a Socket account. There are three tiers:

  • No account (public token): No sign-up required. The Socket CLI supports a built-in public token that provides limited access to CLI features including socket fix, socket scan, sfw, and socket-patch apply. Rate limits and feature restrictions apply compared to a full account, but basic vulnerability scanning and fixing work out of the box. Dashboard access, organization management, and policy configuration are NOT available without an account.
  • Free account: Create one at https://socket.dev. Removes public-token rate limits, enables full dashboard access and organization features. All CLI features are available.
  • Enterprise account: All free account features plus reachability analysis (socket scan reach), policy configuration (socket.yml), and organization-level management.

Read the full file on GitHub · 590 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 · 590 lines · 47 tokens per session scan C ee8f28d2d8cd

Subscribe to this mod's changes

socket-setup is a skill published in the GitHub repository SocketDev/sauce (2 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 6,261 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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