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 ammonhaggerty/a-primer-skills --skill primer-setupgit clone --depth 1 https://github.com/ammonhaggerty/a-primer-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/ammonhaggerty/a-primer-skills/primer-setup)<a href="https://agentmods.dev/skills/ammonhaggerty/a-primer-skills/primer-setup"><img src="https://agentmods.dev/badge/skills/ammonhaggerty/a-primer-skills/primer-setup/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/ammonhaggerty/a-primer-skills/primer-setup"><img src="https://agentmods.dev/badge/skills/ammonhaggerty/a-primer-skills/primer-setup.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00085 | $0.04289 |
| Opus 5 | $0.00043 | $0.02145 |
| Sonnet 5 | $0.00017 | $0.00858 |
| Haiku 4.5 | $0.00009 | $0.00429 |
Grade A, and why
primer-setup 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 9d 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Primer Setup
Overview
One-time guided setup for the AI Primer workflow. Designed for users who may have never opened a terminal. Progressive: present one step at a time, confirm before acting, verify after each change. Idempotent: detect what is already installed and skip completed steps. Safe to re-run at any point — nothing gets duplicated or overwritten.
This skill complements the AI Primer guidebook (Parts 2-3) and prepares the user's machine with every tool, connection, and configuration needed to build and ship full-stack products with Claude.
Design Principles
Five principles govern how this setup operates. Follow all of them throughout the process.
Never assume terminal familiarity
Explain every concept in plain English before executing any command. When a command runs, describe what it does and what the output means. Treat the terminal as a new environment the user is seeing for the first time. Avoid jargon; when technical terms are unavoidable, define them immediately.
One step at a time
Present a single action, explain it, ask permission, execute it, verify the result, then move on. Never batch multiple installs into one step. Never run ahead while the user is still absorbing the previous result. Patience is the default.
Idempotent
Detect what is already installed, configured, and working. Skip those steps entirely with a brief confirmation: "Git is already installed and configured — moving on." If something is installed but broken, fix it rather than re-installing. If something is partially configured, complete the configuration rather than starting over.
Honest
Clearly distinguish what Claude handles automatically from what requires the user to act. Account creation, OAuth flows, and browser-based sign-ins cannot be completed by Claude — say so plainly. Never pretend to do something that requires human interaction. State what will happen, what the user needs to do, and when to come back.
Platform-aware
Detect the operating system first and tailor every instruction accordingly. Mac-first instructions with Windows and Linux alternatives where relevant. Consult references/environment-checks.md for platform-specific detection commands and expected outputs.
What ships with it
4 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.
- 9d ago First seen · 326 lines · 85 tokens per session scan A fb6ca5d3febd
primer-setup is a skill published in the GitHub repository ammonhaggerty/a-primer-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 4,289 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 2026-08-31.
Other skills, from other repositories
skill-dev
Use this skill when creating or refining Claude Code skill definitions. Skills are model-invoked capabilities that Claude activates autonomously based on context. Helps design focused skills with discovery-optimized descriptions, proper directory structures, and supporting resources. Automatically invoked when user…
plugin-dev
Use this skill when creating or refining Claude Code plugins. Plugins are bundled collections of agents, skills, commands, hooks, and MCP servers that provide cohesive functionality. Helps design proper directory structures, plugin.json configuration, marketplace distribution, and installation workflows. Automatically…
command-dev
Use this skill when creating or refining custom Claude Code slash commands. Slash commands are user-invoked reusable prompts that can accept arguments, reference files, and execute bash operations. Helps design command syntax, argument handling, file references, bash execution, and frontmatter configuration.…
agent-dev
Use this skill when creating or refining Claude Code sub-agent definitions. Helps design specialized AI assistants with proper YAML frontmatter, system prompts, tool access, and example-driven descriptions. Automatically invoked when user requests "create an agent", "design a sub-agent", "make a specialist", or…
mcp-tool-dev
Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool schemas, writing tool descriptions, or…
mcp-server-dev
Create MCP servers — multi-tool services exposed via Model Context Protocol. Use this skill whenever users mention MCP servers, building servers, server scaffolding, tool registration, or want to package tools for distribution via uvx or npx. Also use when the conversation involves stdio transport, server lifecycle…