buy-vs-build-dependency

buy-vs-build-dependency is a skill for Claude Code, Codex from stdin/buy-vs-build. It costs 56 tokens per session (1,040 once invoked), scanned A, original, MIT.

A research guide for deciding whether to add a specific open-source or commercial software package as a dependency.

In plain words
What is it for?
Evaluating npm, PyPI, Go, Maven, Cargo, NuGet, RubyGems, or similar packages before adding them to a project.
Why use it?
It checks whether the package is worth owning, including its maintenance, security, licensing, supply-chain risk, and related packages.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: $skill-name invocation.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/dependency-report.js <package> [ecosystem] # ecosystem defaults to npm.

Part of the buy-vs-build plugin — 8 skills, 1 hook shipped together

Good fit Evaluating npm, PyPI, Go, Maven, Cargo, NuGet, RubyGems, or similar packages before adding them to a project.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/stdin/buy-vs-build
agentmods
npx agentmods add skills/stdin/buy-vs-build/buy-vs-build-dependency

Made for: Claude Code, Codex.

Or install buy-vs-build, the plugin that ships this one along with the rest of its 8 skills, 1 hook.

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 buy-vs-build-dependency

README.md
[![agentmods](https://agentmods.dev/badge/skills/stdin/buy-vs-build/buy-vs-build-dependency/github.svg)](https://agentmods.dev/skills/stdin/buy-vs-build/buy-vs-build-dependency)
Your own site
<a href="https://agentmods.dev/skills/stdin/buy-vs-build/buy-vs-build-dependency"><img src="https://agentmods.dev/badge/skills/stdin/buy-vs-build/buy-vs-build-dependency/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 buy-vs-build-dependency

Your own site · 80×15
<a href="https://agentmods.dev/skills/stdin/buy-vs-build/buy-vs-build-dependency"><img src="https://agentmods.dev/badge/skills/stdin/buy-vs-build/buy-vs-build-dependency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,040 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 $0.00056 $0.01040
Opus 5 $0.00028 $0.00520
Sonnet 5 $0.00011 $0.00208
Haiku 4.5 $0.00006 $0.00104

Measured 10d ago against content hash 4667007475ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

buy-vs-build-dependency 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.

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.

plugins/buy-vs-build/skills/buy-vs-build-dependency/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Buy vs Build — Dependency Research

Adding a dependency means adopting its bugs, its maintainers' availability, its security posture, and its whole transitive tree. Research it before you own it. This checklist is the union of two best-in-class frameworks — Russ Cox, "Our Software Dependency Problem" (research.swtch.com/deps), and the OpenSSF "Concise Guide for Evaluating Open Source Software" (best.openssf.org) — plus bus-factor/sustainability research.

This applies to any ecosystem — npm, PyPI, Go modules, Maven, Cargo, NuGet, RubyGems, or anything else. You do the research: gather the signals below from the package's registry, its source repository, deps.dev, and OSV, then judge. The helper automates supported registries, but the checklist — and the judgment — is yours regardless of language.

Start by trying to avoid it

The cheapest dependency is the one you don't add. Before researching a package, confirm a lower rung does not already cover the need: a built-in, a native platform feature, or an already-installed dependency. Reach for a new dependency only when it clearly lowers total cost of ownership, and never for a few clear lines you could own outright (remember left-pad).

The checklist

Fit & necessity

  • Does it solve the actual requirement without large unused surface area?
  • Is the API well-designed, documented, and stable (stable APIs make security upgrades cheap)?
  • Chosen for fit, not hype or popularity alone.

Maintenance & health

  • Active development: meaningful commits and a release within the last ~12 months.
  • Responsive maintainers: reasonable issue/PR turnaround.
  • Bus factor > 1: multiple active maintainers, ideally from different orgs. Most popular OSS has a truck factor of 1–2 (Avelino et al., ICPC 2016) — treat a single maintainer as real risk.
  • Funded/sustainable enough to keep going (sponsors, a foundation, paid maintainers).
  • Real adoption: downloads and dependents (more eyes, more real-world testing).

Read the full file on GitHub · 89 lines

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 · 89 lines · 56 tokens per session scan A 4667007475ed

Subscribe to this mod's changes

buy-vs-build-dependency is a skill published in the GitHub repository stdin/buy-vs-build (3 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 1,040 once invoked, about $0.0003 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.