atlas.deps

atlas.deps is a command for Claude Code from lis186/SourceAtlas. It costs 9 tokens per session (5,554 once invoked), scanned A, original, MIT.

A command that examines how a named library, framework, or software development kit is used in a codebase to support upgrade planning. It can load a saved result from the .sourceatlas/ cache unless forced to re-run the analysis.

In plain words
What is it for?
Use it before upgrading a dependency to analyze its usage, read or refresh cached results, and save the analysis for later.
Why use it?
It provides evidence about where a dependency is used and avoids repeating recent analysis when a cached result is available. The required file-and-line references make findings easier to verify.

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.deps
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.deps

README.md
[![agentmods](https://agentmods.dev/badge/commands/lis186/sourceatlas/atlas.deps.svg)](https://agentmods.dev/commands/lis186/sourceatlas/atlas.deps)
Your own site
<a href="https://agentmods.dev/commands/lis186/sourceatlas/atlas.deps"><img src="https://agentmods.dev/badge/commands/lis186/sourceatlas/atlas.deps.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,554 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 $0.00009 $0.05554
Opus 5 $0.00005 $0.02777
Sonnet 5 $0.00002 $0.01111
Haiku 4.5 $0.00001 $0.00555

Measured 5d ago against content hash 3f48ec2ee119, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atlas.deps 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.

.claude/commands/atlas.deps.md · 728 lines

How it starts

The opening of the file, as written. The whole thing — 728 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SourceAtlas: Dependency Analysis

Constitution: This command operates under ANALYSIS_CONSTITUTION.md v1.1

Key principles enforced:

  • Article IV: Evidence Format Requirements (file:line references)
  • Article V: Output Format (YAML)

Context

Arguments: ${ARGUMENTS}

Goal: Analyze how a specific library, framework, or SDK is used in the codebase to facilitate upgrade planning.


Cache Check (Highest Priority)

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

  1. Extract dependency name from $ARGUMENTS (remove --save, --force)

  2. Convert to filename: spaces→-, to, lowercase, remove special chars, truncate to 50 chars

    • Example: "react"react.md
    • Example: "iOS 16 → 17"ios-16-to-17.md
    • Example: "Python 3.12"python-3-12.md
  3. Check cache:

    ls -la .sourceatlas/deps/{name}.md 2>/dev/null
    
  4. If cache exists:

    • Calculate days since creation
    • Read cache content with Read tool
    • Output:
      📁 Loaded from cache: .sourceatlas/deps/{name}.md (N days ago)
      💡 To re-analyze, add --force
      
    • If older than 30 days, also show:
      ⚠️ Cache is older than 30 days, recommend re-analysis
      
    • Then output:
      ---
      [Cache content]
      
    • Stop here, do not proceed with analysis
  5. If cache does not exist: Continue with analysis below

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


Your Task

Phase 0: Rule Confirmation

IMPORTANT: Before starting inventory, confirm analysis rules. This ensures results meet user needs.

Step 0.1: Identify Upgrade Type

Based on ${ARGUMENTS}:

Input Pattern Type Rules to Confirm
iOS 17, iOS 16 → 17 iOS Minimum Version Upgrade Removable #available, deprecated APIs, new API opportunities
iOS SDK 26, Xcode 16 SDK/Compiler Upgrade Compilation warnings, Swift version changes, new syntax
react 17 → 18, pandas 1.x → 2.x Major Version Upgrade Breaking changes, deprecated APIs, new patterns
react, pandas (no version) Usage Inventory Simply list usage points, no upgrade analysis

Read the full file on GitHub · 728 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. 5d ago First seen · 728 lines · 0 tokens per session scan A 3f48ec2ee119

Subscribe to this mod's changes

atlas.deps is a command published in the GitHub repository lis186/SourceAtlas (48 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 5,554 once invoked, about $0.0000 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.