index-atlas

index-atlas is a skill for Claude Code from traviswye/ContextAtlas. It costs 141 tokens per session (7,322 once invoked), scanned A, original, MIT.

A Claude Code skill that extracts architectural claims from a code project and saves them as an architecture index. It examines architecture decision records, documentation in source-code symbols, and selected commit messages in required phases.

In plain words
What is it for?
Use it to build or update an architecture index during a Claude Code session. For command-line, continuous-integration, or scripting workflows, the input directs users to the separate ContextAtlas CLI.
Why use it?
It reduces the need to reconstruct a project’s design decisions by reading scattered documents, code comments, and version history manually. It runs within a Claude Code session without needing an Anthropic API key.

Skill for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; mentions Claude Code.

Good fit Use it to build or update an architecture index during a Claude Code session. For command-line, continuous-integration, or scripting workflows, the input directs users to the separate ContextAtlas CLI.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/traviswye/contextatlas/index-atlas
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.

Any agent
npx skills add traviswye/ContextAtlas --skill index-atlas
Clone the repo
git clone --depth 1 https://github.com/traviswye/ContextAtlas

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 index-atlas

README.md
[![agentmods](https://agentmods.dev/badge/skills/traviswye/contextatlas/index-atlas/github.svg)](https://agentmods.dev/skills/traviswye/contextatlas/index-atlas)
Your own site
<a href="https://agentmods.dev/skills/traviswye/contextatlas/index-atlas"><img src="https://agentmods.dev/badge/skills/traviswye/contextatlas/index-atlas/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for index-atlas

Your own site · 80×15
<a href="https://agentmods.dev/skills/traviswye/contextatlas/index-atlas"><img src="https://agentmods.dev/badge/skills/traviswye/contextatlas/index-atlas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,322 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 $0.00141 $0.07322
Opus 5 $0.00071 $0.03661
Sonnet 5 $0.00028 $0.01464
Haiku 4.5 $0.00014 $0.00732

Measured 11d ago against content hash c39c90058e4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

index-atlas 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 11d 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/skills/index-atlas/SKILL.md · 662 lines

How it starts

The opening of the file, as written. The whole thing — 662 lines — stays where its author put it; the contents beside it link to each section on GitHub.

index-atlas — ContextAtlas extraction via Claude Code session

When to use this skill

You're running ContextAtlas extraction inside your Claude Code session. User invoked you via /index-atlas slash command directly, OR via contextatlas project context surfacing in their session.

This is THE canonical entry point for subscription-bounded extraction. The contextatlas CLI binary uses Anthropic API direct extraction (different cost model; not this skill's concern). Per ADR-02 v0.7 amendment §Decision: extraction has two entry points; each entry point uses the appropriate cost model for its invocation context.

If user is asking how to extract atlas.json:

  • They're working in Claude Code session right now → invoke this skill
  • They want CLI / CI/CD / scripting workflow → tell them to use contextatlas index from terminal (uses Anthropic API direct; requires ANTHROPIC_API_KEY env var)

What this skill does

Substrate-equivalent extraction at /index-atlas surface per v0.7.1 Path D closure. Three MANDATORY phases (A → B → C). Do not advance until the prior phase substantively completes:

  • Phase A — Source-document walk via contextatlas list- extraction-sources CLI Bash gate + manifest consumption via Read tool. Per-source enumeration discipline produces the full source registry across all three streams (ADRs + source-symbol docstrings + filtered commit messages) before any extraction call. Phase A IS the iteration discipline that closes the v0.7 Step 2.3.b.0 substrate-equivalence regression falsified at v0.8 Step 1.1.b factorial three-repo empirical.

  • Phase B — Per-source extraction loop. For each source in the manifest, one canonical EXTRACTION_PROMPT invocation against the source content; aggregate per-source claims into atlas.json. The per-source iteration IS the mechanical floor — CLI's per- call API loop is its mechanical floor by construction; Phase B per-source reasoning loop is the subscription-bounded equivalent.

Read the full file on GitHub · 662 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. 11d ago First seen · 662 lines · 141 tokens per session scan A c39c90058e4a

Subscribe to this mod's changes

index-atlas is a skill published in the GitHub repository traviswye/ContextAtlas (7 stars, last pushed 3mo ago), licensed MIT. It adds 141 tokens to every session and 7,322 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories