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 mattgierhart/PRD-driven-context-engineering --skill prd-v06-environment-setupgit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/prd-v06-environment-setup)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v06-environment-setup"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v06-environment-setup.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00114 | $0.02658 |
| Opus 5 | $0.00057 | $0.01329 |
| Sonnet 5 | $0.00023 | $0.00532 |
| Haiku 4.5 | $0.00011 | $0.00266 |
Grade C, and why
prd-v06-environment-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 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.
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.
Install: `curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash && nvm install 20` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Install: `curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash && nvm install 20` How it starts
The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Environment Setup
Position in workflow: v0.6 Architecture Design / Technical Specification → v0.6 Environment Setup → v0.7 Build Execution
Environment setup documents the tools, packages, and configurations developers need to work on the project. This eliminates environment drift and speeds up onboarding.
Consumes
This skill requires prior work from v0.5-v0.6:
- TECH-* technology decisions (from v0.5 Technical Stack Selection) — Choices for frontend/backend/database/CI/CD determine which tools, languages, and package managers developers need
- ARC-* architecture decisions (from v0.6 Architecture Design) — Architectural patterns (monolith vs microservices, container strategy, deployment topology) inform infrastructure and scripting needs
This skill assumes v0.5 Technical Stack Selection is complete with TECH- entries specifying the tech stack.
Produces
This skill creates/updates:
- ENV-001: Development Environment — Local setup specification with CLIs (global), packages (per-project), config files, verification steps. Enables consistent development experience across team
- ENV-002: CI/CD Pipeline (optional) — Automated testing and deployment workflow specifications with required secrets and pipeline stages
- ENV-003: Production Infrastructure (optional) — Production hosting, environment variables, services, and deployment topology
All ENV- entries are specifications, not confidence-based. They are:
- Concrete and verifiable (each CLI/package has an install command; each config file has a purpose)
- Preferring CLIs over MCPs (standard tools work in CI/CD; MCPs don't scale)
- Per-project, not global (package managers install dependencies in the project, not globally)
Example ENV-001 entry (Development Environment):
ENV-001: Development Environment
Category: Development Setup
Status: Approved | Date: 2026-02-26
Owner: Engineering Team
Purpose:
Local development setup for team consistency and AI agent understanding.
CLIs (Global, install once):
- Node.js 20.x: https://nodejs.org — Language runtime
Install: `curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash && nvm install 20`
Verify: `node --version`
- mise: https://mise.jdx.dev — Version manager
Install: `curl https://mise.jdx.dev/install.sh | sh`
Verify: `mise --version`
Packages (Per-Project):
- typescript: Type checking (devDependency)
- eslint, prettier: Code quality (devDependencies)
- jest: Testing framework (devDependency)
- Listed in package.json, installed via: `npm install`
Configuration Files:
| File | Purpose |
|------|---------|
| package.json | Dependencies, scripts, project metadata |
| tsconfig.json | TypeScript compiler options |
| .eslintrc.json | Linting rules |
| .prettierrc | Code formatting rules |
| .env.example | Template for environment variables |
Scripts:
{
"validate": "npm run lint && npm run type-check",
"lint": "eslint src/",
"fix": "eslint src/ --fix && prettier --write src/",
"type-check": "tsc --noEmit",
"test": "jest",
"dev": "next dev",
"build": "next build"
}
Verification:
# 1. Check global CLIs
node --version
mise --version
# 2. Check per-project packages
npm list | head -20
# 3. Run validation
npm run validate
# 4. Run tests
npm run test
Related IDs: TECH-001 (Next.js), TECH-002 (TypeScript), ARC-001 (monolith structure)
What ships with it
2 files 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.
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 · 354 lines · 114 tokens per session scan C 61ec4e16427f
prd-v06-environment-setup is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 7d ago), licensed MIT. It adds 114 tokens to every session and 2,658 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
aiwg-regenerate-copilot
Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.