atlas.history

atlas.history is a command for Claude Code from lis186/SourceAtlas. It costs 16 tokens per session (4,753 once invoked), scanned A, original, MIT.

A command that uses Git history to report frequently changed files, files changed together, and recent contributors.

In plain words
What is it for?
Use it to investigate repository hotspots, temporal coupling, and which developers have recently worked on particular areas.
Why use it?
It helps reveal risky code areas, hidden dependencies, and where project knowledge is concentrated.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool; positional $N argument.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Constitution**: This command operates under [ANALYSIS_CONSTITUTION.md](../../ANALYSIS_CONSTITUTION.md) v1.0.

Good fit Use it to investigate repository hotspots, temporal coupling, and which developers have recently worked on particular areas.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/lis186/SourceAtlas
agentmods
npx agentmods add commands/lis186/sourceatlas/atlas.history

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.history

README.md
[![agentmods](https://agentmods.dev/badge/commands/lis186/sourceatlas/atlas.history.svg)](https://agentmods.dev/commands/lis186/sourceatlas/atlas.history)
Your own site
<a href="https://agentmods.dev/commands/lis186/sourceatlas/atlas.history"><img src="https://agentmods.dev/badge/commands/lis186/sourceatlas/atlas.history.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,753 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00016 $0.04753
Opus 5 $0.00008 $0.02377
Sonnet 5 $0.00003 $0.00951
Haiku 4.5 $0.00002 $0.00475

Measured 8d ago against content hash f5c50945ed58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

atlas.history 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 8d 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.history.md · 622 lines

How it starts

The opening of the file, as written. The whole thing — 622 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SourceAtlas: Smart Temporal Analysis (Git History)

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

Key principles enforced:

  • Article II: Mandatory directory exclusions (git log filtering)
  • Article IV: Evidence format (commit hash, file:line references)
  • Article V: Output format (Markdown reports)
  • Article VI: Scale awareness (limit analysis scope for large projects)

Context

Analysis Scope: $ARGUMENTS (default: entire repository)

Goal: Provide actionable insights from git history to help developers understand:

  1. Hotspots - Files changed most frequently (likely complex/risky)
  2. Temporal Coupling - Files that change together (hidden dependencies)
  3. Recent Contributors - Who has knowledge of which areas

Time Limit: Complete in 5-10 minutes.

Prerequisite: code-maat must be installed. If not found, ask user permission before installing.


Cache Check (Highest Priority)

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

  1. Cache path is fixed: .sourceatlas/history.md

  2. Check cache:

    ls -la .sourceatlas/history.md 2>/dev/null
    
  3. If cache exists:

    • Calculate days since creation
    • Use Read tool to load cache content
    • Output:
      📁 Loading cache: .sourceatlas/history.md (N days ago)
      💡 To re-analyze, add --force
      
    • If over 30 days old, additionally display:
      ⚠️ 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 analysis workflow below

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


Your Task

You are SourceAtlas History Analyzer, specialized in extracting insights from git commit history using code-maat.

Help the user understand:

  1. Which files are "hotspots" (frequently changed, likely complex)
  2. Which files have hidden temporal coupling (change together)
  3. Who has recent knowledge of different areas
  4. Risk areas that need attention

Read the full file on GitHub · 622 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. 8d ago First seen · 622 lines · 16 tokens per session scan A f5c50945ed58

Subscribe to this mod's changes

atlas.history is a command published in the GitHub repository lis186/SourceAtlas (48 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 4,753 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.