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.
npx skills add cosmicstack-labs/mercury-agent-skills --skill before-you-buildgit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skillsWrote 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.
[](https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/before-you-build)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/before-you-build"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/before-you-build/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.
<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/before-you-build"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/before-you-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 148 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01979 |
| Opus 5 | $0.00016 | $0.00989 |
| Sonnet 5 | $0.00007 | $0.00396 |
| Haiku 4.5 | $0.00003 | $0.00198 |
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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before You Build
Purpose
Use this skill before an agent starts building a product, feature, SaaS tool, AI app, side project, or startup idea.
The goal is not to block shipping. The goal is to avoid spending engineering time on an idea whose biggest risk is still outside the codebase.
Before implementation, produce:
- A short risk verdict
- A score across product risk dimensions
- The riskiest assumption
- The smallest validation step worth doing next
- A clear build, test, or stop recommendation
When To Use
Use this skill when the user says they want to:
- Build a new product or feature
- Add an AI workflow to an existing product
- Turn an idea into an MVP
- Copy a competitor or trend
- Ship a side project quickly
- Start coding before talking to users
- Ask whether an idea is worth building
- Decide between multiple product bets
Do not use this for:
- Pure code debugging
- Refactoring existing implementation
- UI polish after the product bet is already validated
- Legal, financial, medical, or security review
- Choosing a tech stack
Core Principle
Most early product failures are not caused by missing code.
They usually come from one or more of these gaps:
- The buyer does not feel the problem strongly enough
- The user likes the idea but will not pay
- The product depends on a platform that can change access
- The founder has no repeatable channel to reach buyers
- The workflow is useful once but does not create repeat use
- The trust burden is higher than the product can carry
- The feature is nice to have but not a decision-changing reason to buy
Your job is to find the biggest unknown before implementation expands the cost of being wrong.
Inputs To Ask For
If the user has not provided enough context, ask for the minimum needed:
- What is being built?
- Who is the target user or buyer?
- What painful job does it solve?
- What will the user do differently after adopting it?
- How will the product reach the first 10 real users?
- How will it make money or justify internal investment?
- What evidence already exists?
- What would make the user abandon the product?
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.
- 8d ago First seen · 285 lines · 33 tokens per session scan A 4f37326b44d1
before-you-build is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 17d ago), licensed MIT. It adds 33 tokens to every session and 1,979 once invoked, about $0.0002 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.
Other skills, from other repositories
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
template-instantiation
Creates .NET projects from templates with validated parameters, smart defaults, Central Package Management adaptation, and latest NuGet version resolution. USE FOR: creating new dotnet projects, scaffolding solutions with multiple projects, installing or uninstalling template packages, creating projects that respect…
note-improvement
Capture an out-of-scope improvement opportunity so it doesn't get lost. Use when the user asks to "note improvement", "save improvement", "track this for later", "remember this improvement", "note this idea", "log improvement", "backlog this", or "park this idea". Also invoke proactively when noticing something…
turborepo-monorepo
Provides comprehensive Turborepo monorepo management guidance for TypeScript/JavaScript projects. Use when creating Turborepo workspaces, configuring turbo.json tasks, setting up Next.js/NestJS apps, managing test pipelines (Vitest/Jest), configuring CI/CD, implementing remote caching, or optimizing build performance…
handover-admin
Generate comprehensive admin documentation for AEM Edge Delivery Services project handover. Use when handing over admin responsibilities, onboarding a new site administrator, or documenting admin procedures — e.g., "admin guide", "admin documentation", "admin handover".
project-context-setup
Scaffolds per-repository agent context so coding agents share the same issue tracker rules, triage label vocabulary, domain glossary, ADR layout, and handoff conventions. Triggers on: "set up project context", "configure agent docs", "create CONTEXT.md", "setup agent workflow", "agent issue tracker setup", "triage…