atlas.impact

atlas.impact is a command for Claude Code from lis186/SourceAtlas. It costs 11 tokens per session (6,786 once invoked), scanned A, original, MIT.

A command that maps which parts of a codebase may be affected when a file or component changes, using references between code files.

In plain words
What is it for?
Use it to check the impact of a planned change and produce file-and-line evidence of related code. It can also reuse saved analysis results when available.
Why use it?
It helps you see possible knock-on effects before editing code, so you can review and test the relevant areas instead of guessing.

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.impact
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.impact

README.md
[![agentmods](https://agentmods.dev/badge/commands/lis186/sourceatlas/atlas.impact.svg)](https://agentmods.dev/commands/lis186/sourceatlas/atlas.impact)
Your own site
<a href="https://agentmods.dev/commands/lis186/sourceatlas/atlas.impact"><img src="https://agentmods.dev/badge/commands/lis186/sourceatlas/atlas.impact.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,786 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 $0.00011 $0.06786
Opus 5 $0.00005 $0.03393
Sonnet 5 $0.00002 $0.01357
Haiku 4.5 $0.00001 $0.00679

Measured 4d ago against content hash 12045a7e0c13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atlas.impact 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.impact.md · 903 lines

How it starts

The opening of the file, as written. The whole thing — 903 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SourceAtlas: Impact Analysis (Static Dependencies)

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

Key principles enforced:

  • Article I: Structure over details (track dependencies, not implementation)
  • Article II: Mandatory directory exclusion
  • Article IV: Evidence format (file:line references)
  • Article VI: Scale awareness (limit tracking depth for large projects)

Context

Analysis Target: $ARGUMENTS

Goal: Identify all code affected by changes to the target component through static dependency analysis.

Time Limit: Complete in 5-10 minutes.


Cache Check (Highest Priority)

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

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

  2. Convert to filename: spaces → -, slashes → -, lowercase, remove {}, truncate to 50 characters

    • Example: "User model"user-model.md
    • Example: "api /api/users/{id}"api-users-id.md
  3. Check cache:

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

    • Calculate days since creation
    • Read cache content using Read tool
    • Output:
      📁 Loading from cache: .sourceatlas/impact/{name}.md (N days ago)
      💡 Use --force to reanalyze --force
      
    • If over 30 days, additionally display:
      ⚠️ Cache is over 30 days old, recommend reanalysis
      
    • Then output:
      ---
      [Cache content]
      
    • End, do not execute subsequent analysis
  5. If cache does not exist: Continue with analysis below

If arguments contain --force: Skip cache check, run analysis directly


Your Task

You are SourceAtlas Impact Analyzer, specialized in tracing static dependencies and identifying change impact.

Help the user understand:

  1. What code directly depends on the target
  2. What code indirectly depends on it (call chains)
  3. Which tests need updating
  4. Migration checklist and risk assessment

Read the full file on GitHub · 903 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 · 903 lines · 0 tokens per session scan A 12045a7e0c13

Subscribe to this mod's changes

atlas.impact is a command published in the GitHub repository lis186/SourceAtlas (48 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 6,786 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.