What is SourceAtlas CLAUDE.md?

A contributor guide for SourceAtlas, a code-analysis tool that builds a compact understanding of a project. It documents important files, commands, analysis types, and the project's development rules.

Use it when developing SourceAtlas to run its overview, pattern, flow, history, impact, dependency, listing, and reset analyses, and to follow its contribution rules.

It gives coding agents the project context and commands they need before changing SourceAtlas. It also prevents them from violating the repository's GitButler workflow.

SourceAtlas CLAUDE.md — Instructions file by lis186

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 instructions/lis186/sourceatlas/claude-md

Clone the repo

git clone --depth 1 https://github.com/lis186/SourceAtlas

Per session 731 This file is loaded in full into every session.

When invoked 731 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00731	$0.00731
Opus 5	$0.00365	$0.00365
Sonnet 5	$0.00146	$0.00146
Haiku 4.5	$0.00073	$0.00073

Measured 3d ago against content hash c2a88c67402a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SourceAtlas CLAUDE.md 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 3d 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.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

AI collaboration guide for SourceAtlas development.

What is SourceAtlas

AI-optimized codebase analysis tool - scan <5% of files to achieve 70-95% understanding using information theory principles.

Current Version: v2.13.1 (2026-03-09)

Key Files

File	Purpose
`ANALYSIS_CONSTITUTION.md`	Immutable analysis principles (7 Articles)
`PROMPTS.md`	Stage 0-1-2 prompt templates
`PRD.md`	Product requirements
`USAGE_GUIDE.md`	User documentation
`dev-notes/ROADMAP.md`	Future plans
`dev-notes/HISTORY.md`	Version history

Commands

/atlas.overview  - Project fingerprint (Stage 0)
/atlas.pattern   - Learn design patterns
/atlas.flow      - Flow tracing (11 modes)
/atlas.history   - Git temporal analysis
/atlas.impact    - Change impact analysis
/atlas.deps      - Dependency analysis
/atlas.list      - List saved analyses
/atlas.reset     - Clear saved analyses

All commands auto-save to .sourceatlas/. Use --force to skip cache and re-analyze.

Must Follow

GitButler Workflow

Never use git commit - GitButler manages all commits
Focus on code, let GitButler handle version control
When done, stop and let GitButler hooks execute

Analysis Principles (from Constitution)

Information Theory - High-entropy files first (configs, docs, models)
Scale-Aware - TINY 50%, SMALL 20%, MEDIUM 10%, LARGE 5%, VERY_LARGE 3%
Evidence-Based - Every claim needs file:line reference
Exclude Always - .venv, node_modules, __pycache__

Implementation Rules

Standards over custom (YAML, Markdown)
Test on 3+ real projects
Document while developing
Use validate-constitution.sh for compliance

Key Learnings (v1.0)

Information theory works - <5% scan → 70-80% understanding
Scale-awareness critical - Different strategies per size
YAML > TOON - Standard ecosystem > 14% token savings
Benchmarking reveals truth - Test on real projects
AI collaboration detectable - Level 0-4 maturity model

Read the full file on GitHub · 88 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.

3d ago First seen · 88 lines · 731 tokens per session scan A c2a88c67402a

Subscribe to this mod's changes

SourceAtlas CLAUDE.md is an instructions file published in the GitHub repository lis186/SourceAtlas (47 stars, last pushed 1mo ago), licensed MIT. It adds 731 tokens to every session, about $0.0037 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.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

SourceAtlas CLAUDE.md