prime-atlas

prime-atlas is a skill for Claude Code from traviswye/ContextAtlas. It costs 100 tokens per session (2,434 once invoked), scanned A, original, MIT.

A per-session setup check for ContextAtlas, a code-understanding system that maps symbols, intent, and change impact in a repository. It verifies the connection and explains when to use its three tools.

In plain words
What is it for?
Use it at the start of a Claude Code session to check ContextAtlas and learn how to inspect code symbols, find relevant code by intent, and assess the effects of a change.
Why use it?
It confirms that the repository's code map is available before architectural work begins. It also clarifies whether the current task needs symbol context, intent-based search, or impact analysis.

Skill for Claude Code

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

Good fit Use it at the start of a Claude Code session to check ContextAtlas and learn how to inspect code symbols, find relevant code by intent, and assess the effects of a change.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/traviswye/contextatlas/prime-atlas"><img src="https://agentmods.dev/badge/skills/traviswye/contextatlas/prime-atlas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,434 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 $0.00100 $0.02434
Opus 5 $0.00050 $0.01217
Sonnet 5 $0.00020 $0.00487
Haiku 4.5 $0.00010 $0.00243

Measured 11d ago against content hash 12d693aabf21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prime-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/prime-atlas/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

prime-atlas — Per-session ContextAtlas priming + MCP verification

When to use this skill

You're starting a Claude Code session in a ContextAtlas-configured repo. User invoked you via /prime-atlas slash command at session open, OR via contextatlas project context surfacing in their session.

This is THE canonical per-session entry point. Run once per session before architectural work. Pattern: cohort users run contextatlas init once per repo (substantive scaffold) + /index-atlas to build the atlas substrate + /prime-atlas at the start of each session post-init to verify the MCP connection + prime the session with when-to-use guidance for the three ContextAtlas MCP tools.

If user is asking how to use ContextAtlas tools in this session:

  • They want to verify setup is working + want introduction to the tools → invoke this skill
  • They want to extract atlas.json (first-time setup or refresh after ADR/code changes) → tell them to run /index-atlas first
  • They want to generate ADRs (new repo without ADRs) → tell them to run /generate-adrs first

What this skill does

  1. Loads the atlas substrate via Read tool against:

    .contextatlas/atlas.json (relative to cwd)

    This file is produced by contextatlas index (CLI) or /index-atlas (Skill) — the substantive ContextAtlas substrate. If the file is absent → instruct user to run contextatlas init then /index-atlas first, and exit this skill (do NOT proceed to probe step).

  2. Validates the atlas substrate shape:

    • JSON parses successfully
    • Top-level symbols array exists AND has ≥1 entry
    • If symbols array is empty → atlas built but empty; instruct user to run /index-atlas to populate, and exit.
  3. Verifies .mcp.json via Read tool against:

    .mcp.json (at repo root)

    Verify the file exists + contains a mcpServers.contextatlas entry. If absent OR missing the contextatlas entry → instruct user to run contextatlas init (which idempotently upserts the entry per the canonical mcp-registration substrate), and exit.

Read the full file on GitHub · 216 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 · 216 lines · 100 tokens per session scan A 12d693aabf21

Subscribe to this mod's changes

prime-atlas is a skill published in the GitHub repository traviswye/ContextAtlas (7 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 2,434 once invoked, about $0.0005 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