before-you-build

before-you-build is a skill for Claude Code, Codex from wshobson/agents. It costs 75 tokens per session (569 once invoked), scanned A, original, MIT.

A pre-build review that examines whether a proposed product or feature is worth building before implementation starts.

In plain words
What is it for?
Use it to identify the riskiest assumption, choose a small validation step, and decide which parts of a product, MVP, landing page, internal tool, or agent workflow to delay.
Why use it?
It helps uncover weak demand, unclear positioning, uncertain revenue, retention, trust, or distribution before development time is spent.

Skill for Claude CodeCodex

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

Part of the before-you-build plugin — 1 skill shipped together

Good fit Use it to identify the riskiest assumption, choose a small validation step…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wshobson/agents/before-you-build
About the project

Agentic Plugin Marketplace is a collection of reusable plugins, agents, skills, commands, and rules for coding-agent tools including Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, and GitHub Copilot. It is for developers assembling agentic workflows across multiple harnesses from shared Markdown sources, and the catalogue entries are examples or subsets of those workflow components.

wshobson/agents · 39,461 stars · on GitHub · sethhobson.com

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 wshobson/agents --skill before-you-build
Clone the repo
git clone --depth 1 https://github.com/wshobson/agents

Made for: Claude Code, Codex.

Or install before-you-build, the plugin that ships this one along with the rest of its 1 skill.

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 before-you-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/wshobson/agents/before-you-build.svg)](https://agentmods.dev/skills/wshobson/agents/before-you-build)
Your own site
<a href="https://agentmods.dev/skills/wshobson/agents/before-you-build"><img src="https://agentmods.dev/badge/skills/wshobson/agents/before-you-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 569 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 $0.00075 $0.00569
Opus 5 $0.00037 $0.00284
Sonnet 5 $0.00015 $0.00114
Haiku 4.5 $0.00007 $0.00057

Measured 3d ago against content hash e5ce9fc6e4ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

before-you-build 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 3d 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/before-you-build/skills/before-you-build/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before You Build

Run a compact pre-mortem before implementation. The goal is not to block building; it is to identify the highest-risk assumption, the smallest validation step, and the build scope that should be delayed until evidence improves.

When To Use

Use this skill when a user asks to build or ship:

  • A new product, MVP, prototype, landing page, SaaS app, marketplace, content site, agent workflow, or internal tool
  • A major feature with unclear adoption, revenue, retention, trust, or distribution impact
  • A public launch asset where weak positioning could waste development or promotion effort

Skip this skill when the task is a narrow implementation fix, refactor, test repair, dependency update, or already-validated change with clear acceptance criteria.

Risk Checklist

Review the idea across these risks:

  • Demand: Is there evidence that a specific buyer or user urgently wants this?
  • Positioning: Can the target user understand what it is and why it matters in one sentence?
  • Monetization: Is there a credible path to payment, budget, or strategic value?
  • Retention: Is there a reason users would return after the first try?
  • Trust: Does the product require credibility, data access, integrations, or behavior change that users may resist?
  • Distribution: Is there a repeatable way to reach the target user?
  • Feature adoption: For feature work, will the feature change user behavior or just add surface area?

If the verdict is not obvious, use references/risk-checklist.md for deeper questions.

Output Format

Keep the response short and decision-oriented:

  1. Risk verdict: Low, medium, or high risk, with one sentence explaining why.
  2. Main assumption: The single assumption most likely to break the project.
  3. Evidence to find first: The smallest useful signal before building more.
  4. Do next: One concrete validation step or reduced build scope.
  5. Delay: What not to build yet.

Guidance

  • Be direct about weak evidence, but avoid dismissing the user's idea.
  • Prefer smaller validation steps over large research plans.
  • Separate product risk from engineering difficulty.
  • If the idea is already validated, say what evidence makes it lower risk and suggest the smallest implementation slice.
  • If facts are missing, name the missing evidence instead of inventing market claims.

Read the full file on GitHub · 51 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. 3d ago First seen · 51 lines · 75 tokens per session scan A e5ce9fc6e4ef

Subscribe to this mod's changes

before-you-build is a skill published in the GitHub repository wshobson/agents (39,461 stars, last pushed 5d ago), licensed MIT. It adds 75 tokens to every session and 569 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 2026-09-03.