atlas-setup

atlas-setup is a skill for Claude Code, Codex from Blazity/atlas. It costs 34 tokens per session (2,150 once invoked), scanned A, original, MIT.

A skill for setting up or refreshing Atlas, a system that organizes repository guidance, AI memory, and vocabulary files for coding agents.

In plain words
What is it for?
Use it for first-time Atlas setup, repairs, updates, or reviews after major codebase changes.
Why use it?
It separates automatic repository checks from decisions about what the codebase means, helping keep agent-facing documentation aligned with the project.

Skill for Claude CodeCodex

Part of the atlas plugin — 3 skills shipped together

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.

agentmods
npx agentmods add skills/blazity/atlas/atlas-setup
Any agent
npx skills add Blazity/atlas --skill atlas-setup
Clone the repo
git clone --depth 1 https://github.com/Blazity/atlas

Made for: Claude Code, Codex.

Or install atlas, the plugin that ships this one along with the rest of its 3 skills.

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 atlas-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/blazity/atlas/atlas-setup.svg)](https://agentmods.dev/skills/blazity/atlas/atlas-setup)
Your own site
<a href="https://agentmods.dev/skills/blazity/atlas/atlas-setup"><img src="https://agentmods.dev/badge/skills/blazity/atlas/atlas-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,150 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.02150
Opus 5 $0.00017 $0.01075
Sonnet 5 $0.00007 $0.00430
Haiku 4.5 $0.00003 $0.00215

Measured 5d ago against content hash 7042f1eabe0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

atlas-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 5d 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.

.ai/skills/atlas-setup/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set Up Atlas

Overview

Use this skill for first setup and later refreshes. The published CLI owns deterministic structure; this skill owns semantic repository understanding.

Humans and agents use the same deterministic entrypoint. Do not reimplement init, doctor, path repair, symlink repair, or managed file repair inside this skill. Call the CLI through npx, preferring a locally installed @blazity-atlas/core (npx --no-install @blazity-atlas/core …) and falling back to the published package only when none is installed. Every npx --yes @blazity-atlas/core@latest … command in this skill is the fallback spelling of that rule, not an instruction to skip the local copy.

Run the phases below in order.

Phase 1 — Deterministic Bootstrap

Before inspecting repository meaning, announce the deterministic setup steps you are about to run.

From the repository root, run the Atlas CLI. Prefer a locally installed copy so the run works offline and matches the version that shipped this skill:

npx --no-install @blazity-atlas/core doctor

Fall back to the published package only when that fails because the package is not installed locally (npx cannot find it — not when doctor itself reports findings):

npx --yes @blazity-atlas/core@latest doctor

If a fix run rewrites files under the workspace skills directory (a newer published version landed), re-read this skill file before continuing.

Then follow the CLI result:

  • If Atlas is missing or mostly uninitialized, run npx --yes @blazity-atlas/core@latest init.
  • If doctor reports only fixable drift, run npx --yes @blazity-atlas/core@latest doctor --fix.
  • If doctor --fix refuses because of a dirty worktree, stop and ask the user whether to commit, stash, or explicitly rerun with --force. Do not use --force automatically.
  • If doctor reports manual conflicts, summarize those conflicts and stop before semantic setup.
  • Rerun npx --yes @blazity-atlas/core@latest doctor after any init or fix command.
  • Continue only when doctor exits clean. Advisory findings (doctor exits 0) do not count as unclean — they are signals this skill resolves in later phases. Only fixable or manual findings block this phase.

Read the full file on GitHub · 150 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. 5d ago First seen · 150 lines · 34 tokens per session scan A 7042f1eabe0c

Subscribe to this mod's changes

atlas-setup is a skill published in the GitHub repository Blazity/atlas (24 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 2,150 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 2026-08-30.

Related

Other skills, from other repositories

continual-learning

Orchestrate continual learning by delegating transcript mining to agents-memory-updater and writing durable memory to local JSON (never root AGENTS.md Learned sections). USE WHEN continual learning, mine prior chats, maintain agent memory, or the stop hook triggers this skill.

docxology/template · 56 tokens

deep-init

Generate an agent-agnostic, two-tier context layer for a codebase — a lean, always-loaded CLAUDE.md plus a deep, on-demand .ai/docs/ layer (business rules, live DB schema + ORM drift, cross-component workflows, and the WHY: ADRs + a knowledge log), every claim grounded to file:line and verified to exist. Built for…

deepfusionlabs/deep-init · 128 tokens

maintain-project-ai-records

Initialize and maintain lightweight AI work records in a writable project. Use on the first substantive writable task and after meaningful milestones. Do not create records for read-only inspection or trivial answers.

WildPigKing/codex-project-skill-manager · 43 tokens

ackit-context-optimization

Build budgeted context packs and trim instruction bloat for coding agents.

Cynrath/agent-context-kit · 20 tokens

project-memory

Initialize, retrieve, and explicitly update the separate Rootloom Memory plugin's repository-owned architecture, risk, decision, and failure lessons. Use only when explicitly requested. Memory is experimental, advisory, and outside Rootloom Core.

qingye-lab/rootloom · 47 tokens

faf-context

Use FAF project context tools on this server — init, score, sync, discover; claim equals wire.

Wolfe-Jam/rust-faf-mcp · 24 tokens