buy-vs-build-adr

buy-vs-build-adr is a skill for Claude Code, Codex from stdin/buy-vs-build. It costs 58 tokens per session (450 once invoked), scanned A, original, MIT.

A guide for recording a non-obvious technical choice in an Architecture Decision Record, a short document that preserves why a project made the choice.

In plain words
What is it for?
Adding numbered decision notes to docs/decisions/ when choosing a dependency, service, in-house implementation, or one technical approach over another.
Why use it?
It keeps the reasoning and the condition for revisiting a buy-versus-build or dependency decision available after the original discussion is over.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/record-decision.js \.

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

Good fit Adding numbered decision notes to docs/decisions/ when choosing a dependency, service, in-house implementation, or one technical approach over another.

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-adr

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-adr

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/stdin/buy-vs-build/buy-vs-build-adr"><img src="https://agentmods.dev/badge/skills/stdin/buy-vs-build/buy-vs-build-adr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 450 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 $0.00058 $0.00450
Opus 5 $0.00029 $0.00225
Sonnet 5 $0.00012 $0.00090
Haiku 4.5 $0.00006 $0.00045

Measured 11d ago against content hash 4502dad3fce0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

buy-vs-build-adr 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 11d 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-adr/SKILL.md · 58 lines

What it actually says

Buy vs Build ADR

Capture non-obvious buy-vs-build decisions as Architecture Decision Records so the reasoning — and the trigger to revisit it — survives the pull request.

When to record

Record an ADR when a decision is non-obvious or hard to reverse:

  • Adding or removing a dependency.
  • Choosing a commercial service over owning a capability.
  • Building something in-house.
  • Picking one technical option over a comparable one (for example, Server-Sent Events over WebSockets).

Skip it for obvious, trivial, easily reversible choices. An ADR is a few sentences, not an essay — it mirrors the one-line decision note the rule already produces, just durable and reviewable.

How to record

ADRs live in docs/decisions/, numbered sequentially as NNNN-title.md. Use the next free number. Either run the helper:

node scripts/record-decision.js \
  --title "Use Server-Sent Events for the live feed" \
  --rung native-platform \
  --decision "Stream updates with SSE over HTTP." \
  --rejected "WebSockets, because the feed is one-way and full-duplex is unused." \
  --revisit "the feed needs bidirectional messaging."

…or, if no helper is available, create docs/decisions/NNNN-title.md by hand with this shape:

# NNNN. <title>

- Status: Accepted
- Date: <YYYY-MM-DD>
- Rung: <do-nothing|built-in|native-platform|installed-dependency|open-source|commercial|in-house>

## Context

<requirement and constraints>

## Decision

<the option chosen>

**Tradeoff:** <why it wins>
**Rejected:** <next-best option> because <constraint>

## Consequences

Revisit if <specific trigger>.
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. 11d ago First seen · 58 lines · 58 tokens per session scan A 4502dad3fce0

Subscribe to this mod's changes

buy-vs-build-adr is a skill published in the GitHub repository stdin/buy-vs-build (3 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 450 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.