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 agentmods add instructions/versoxbt/claude-initial-setup/agents-mdgit clone --depth 1 https://github.com/VersoXBT/claude-initial-setupWrote 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/instructions/versoxbt/claude-initial-setup/agents-md)<a href="https://agentmods.dev/instructions/versoxbt/claude-initial-setup/agents-md"><img src="https://agentmods.dev/badge/instructions/versoxbt/claude-initial-setup/agents-md.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 | $0.02105 | $0.02105 |
| Opus 5 | $0.01052 | $0.01052 |
| Sonnet 5 | $0.00421 | $0.00421 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
claude-initial-setup AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
A curated library of 75 Claude Code skills across 25 categories, providing coding standards, patterns, and best practices for software development. Skills cover coding style, git workflow, testing, debugging, security, and language-specific patterns for TypeScript, Python, Go, Rust, Java, React/Next.js, Express/Node, FastAPI, Django, Docker, CI/CD, databases, and more.
Development Conventions
Code Style
Immutability
Always create new objects instead of mutating existing ones. Immutability prevents shared-state bugs and enables reliable change detection.
// WRONG: Mutation
function updateUser(user, name) {
user.name = name;
return user;
}
// CORRECT: Immutable update
function updateUser(user, name) {
return { ...user, name };
}
Array operations must also be immutable:
const added = [...items, newItem]; // append
const removed = items.filter(x => x.id !== id); // remove
const updated = items.map(x => // update
x.id === id ? { ...x, name: "new" } : x
);
const sorted = items.toSorted((a, b) => a.name.localeCompare(b.name));
Python: Use @dataclass(frozen=True) and replace() for immutable data.
Go: Use value receivers and return new structs instead of mutating via pointers.
File Organization
- Target 200-400 lines per file, 800 maximum
- Organize by feature/domain, not by type
- Co-locate tests, styles, and types with their source files
- Move code to
shared/only when used by 3+ features
Functions
- Keep functions under 50 lines
- No deep nesting beyond 4 levels
- Name functions with a verb:
getUserById,formatDate,validateEmail
Naming
- Variables describe WHAT, not HOW:
activeUsersnotdata - Booleans use
is/has/can/shouldprefix:isActive,hasPermission - Collections use plural nouns:
users,orderItems - Constants use SCREAMING_SNAKE:
MAX_RETRIES,API_BASE_URL - Follow language-specific casing (camelCase for JS/TS, snake_case for Python, PascalCase for Go exports)
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.
- 3d ago First seen · 269 lines · 2,105 tokens per session scan A 82b72924c024
claude-initial-setup AGENTS.md is an instructions file published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 2,105 tokens to every session, about $0.0105 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 instructions, from other repositories
aider-desk AGENTS.md
AGENTS.md instructions for hotovo/aider-desk, covering agents.md, common commands, development, type checking and linting and formatting.
spellbook AGENTS.md
AGENTS.md instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
sdlc-quality copilot-instructions.md
Instructions for zircote-plugins/sdlc-quality, covering copilot instructions for sdlc plugin, project overview, repository structure, key conventions and rfc 2119 terminology.
swttch CLAUDE.md
Claude Code instructions for Swttch/swttch, covering claude.md, 프로젝트 개요, ★ 핵심 원칙 — cli 동등성 & 공식 지원 비의존 (최우선, 위반 금지), 기록된 예외 and 아키텍처.
skills AGENTS.md
Instructions for CometWorks/skills: You are an experienced developer of Space Engineers in-game scripts, mods, and plugins.
Myco AGENTS.md
Instructions for BreetyGreen/Myco, covering agents.md — orientation for ai agents & contributors, what this project is, architecture (two layers), single source of truth: engine/agents.json and key files.