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.
npx skills add traviswye/ContextAtlas --skill prime-atlasgit clone --depth 1 https://github.com/traviswye/ContextAtlasWrote 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.
[](https://agentmods.dev/skills/traviswye/contextatlas/prime-atlas)<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.
<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>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 5.1 | $0.00100 | $0.02434 |
| Opus 5 | $0.00050 | $0.01217 |
| Sonnet 5 | $0.00020 | $0.00487 |
| Haiku 4.5 | $0.00010 | $0.00243 |
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.
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-atlasfirst - They want to generate ADRs (new repo without ADRs) → tell them to
run
/generate-adrsfirst
What this skill does
-
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 runcontextatlas initthen/index-atlasfirst, and exit this skill (do NOT proceed to probe step). -
Validates the atlas substrate shape:
- JSON parses successfully
- Top-level
symbolsarray exists AND has ≥1 entry - If
symbolsarray is empty → atlas built but empty; instruct user to run/index-atlasto populate, and exit.
-
Verifies
.mcp.jsonvia Read tool against:.mcp.json(at repo root)Verify the file exists + contains a
mcpServers.contextatlasentry. If absent OR missing the contextatlas entry → instruct user to runcontextatlas init(which idempotently upserts the entry per the canonical mcp-registration substrate), and exit.
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.
- 11d ago First seen · 216 lines · 100 tokens per session scan A 12d693aabf21
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.
Other skills, from other repositories
decision-memory
Use when planning, designing, reviewing, or changing code in a repository that keeps ADRs (usually docs/adr) — to load the decisions that already govern the work, check a plan or diff against them, or record a new decision. Also use when a choice feels already-settled and you cannot find where it was settled.
memory-continuity
Preserves cross-session continuity with deterministic MEMORY.md, index.md, and snapshot handoffs under .agentic/memories/.
plan-memory-index
Maintains concise indexed memory entries for applied plans under .agentic/memories/ with clear boundaries between memory and plan sources. Memory retrieval is prioritized before loading historical plan files.
plan
Structured technical planning before implementation — architecture and task breakdown.
architecture-governance
Keep code changes conformant to a repo's real, declared architecture using ArchSteer. Use when starting work in an unfamiliar repo, before finishing/committing an architecturally significant change (new dependency, new data access, new external call, new layer), or when asked about a codebase's architecture, layers…
mpm-adr
Architecture Decision Records (ADRs) — opt-in convention for documenting significant, hard-to-reverse architectural decisions using the Nygard template.