atlas.overview

atlas.overview is a command for Claude Code from lis186/SourceAtlas. It costs 18 tokens per session (4,889 once invoked), scanned A, original, MIT.

A project-overview command scans a small portion of a codebase to build a structured summary of its files, patterns, and key details.

In plain words
What is it for?
Use it to create or refresh a project fingerprint for the current directory or a specified path, optionally saving the result as YAML.
Why use it?
It gives an agent an initial understanding of an unfamiliar project without reading every file, while recording the summary for reuse when requested.

Command for Claude Code

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 commands/lis186/sourceatlas/atlas.overview
Clone the repo
git clone --depth 1 https://github.com/lis186/SourceAtlas

Made for: Claude Code.

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.overview

README.md
[![agentmods](https://agentmods.dev/badge/commands/lis186/sourceatlas/atlas.overview.svg)](https://agentmods.dev/commands/lis186/sourceatlas/atlas.overview)
Your own site
<a href="https://agentmods.dev/commands/lis186/sourceatlas/atlas.overview"><img src="https://agentmods.dev/badge/commands/lis186/sourceatlas/atlas.overview.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,889 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 $0.00018 $0.04889
Opus 5 $0.00009 $0.02445
Sonnet 5 $0.00004 $0.00978
Haiku 4.5 $0.00002 $0.00489

Measured 4d ago against content hash 7528eed135e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atlas.overview 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 4d 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.

.claude/commands/atlas.overview.md · 547 lines

How it starts

The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SourceAtlas: Project Overview (Stage 0 Fingerprint)

Constitution: This command operates under ANALYSIS_CONSTITUTION.md v1.0

Key principles enforced:

  • Article I: High-entropy priority, scan ratio limits
  • Article II: Mandatory directory exclusions
  • Article III: Hypothesis count limits, required elements
  • Article IV: Evidence format requirements

Context

Arguments: ${ARGUMENTS:-.}

Save Mode: Check if --save is in arguments. If present:

  • Remove --save from path argument
  • After analysis, save YAML to .sourceatlas/overview.yaml
  • Create .sourceatlas/ directory if needed

Analysis Target: Parse from arguments (default: current directory)

Goal: Generate a comprehensive project fingerprint by scanning <5% of files to achieve 70-80% understanding in 10-15 minutes.


Cache Check (Highest Priority)

If --force is NOT in arguments, check cache first:

  1. Calculate cache path:

    • No path argument or .: .sourceatlas/overview.yaml
    • With path argument (e.g., src/api): .sourceatlas/overview-src-api.yaml (slashes to -)
  2. Check if cache exists:

    ls -la .sourceatlas/overview.yaml 2>/dev/null
    
  3. If cache exists:

    • Read modification date from ls output
    • Calculate days since modification
    • Use Read tool to read cache content
    • Output:
      📁 Loading cache: .sourceatlas/overview.yaml (N days ago)
      💡 Add --force to re-analyze
      
    • If over 30 days, also show:
      ⚠️ Cache is over 30 days old, recommend re-analysis
      
    • Then output:
      ---
      [cache content]
      
    • End, do not execute subsequent analysis
  4. If cache does not exist: Continue with the analysis flow below

If --force is in arguments: Skip cache check, execute analysis directly


Your Task

Execute Stage 0 Analysis Only - generate a project overview using information theory principles.

Read the full file on GitHub · 547 lines

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. 4d ago First seen · 547 lines · 0 tokens per session scan A 7528eed135e1

Subscribe to this mod's changes

atlas.overview is a command published in the GitHub repository lis186/SourceAtlas (48 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 4,889 once invoked, about $0.0001 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.