Visualize local Codex and Claude Code context usage, open a report, flag warnings, and suggest prompt/tooling optimizations.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add BuilderIO/agent-native --skill context-xray --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Context Xray?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/builderio-context-xray-agent-native)More formats (shields.io, HTML) on the badges page.
---
name: context-xray
description: >-
Visualize local Codex and Claude Code context usage, open a report, flag
warnings, and suggest prompt/tooling optimizations.
metadata:
visibility: exported
---
# Context X-Ray
Use Context X-Ray when a local coding-agent thread is getting large or the user
wants to understand where context is going.
## Setup
Recommended install path:
```bash
npx @agent-native/core@latest skills add context-xray --client all
```
That installs a local `context-xray` command plus Codex/Claude skills and slash
commands. It does not need hosted auth or a remote MCP connector to read local
transcript files.
Use `--scope project` when you only want project `.agents` skill and command
artifacts added to the current repo.
## Run
Current or most recent local thread:
```bash
context-xray --open
```
Recent thread picker:
```bash
context-xray threads --open
```
Weekly trends:
```bash
context-xray trends --since 7d --open
```
`--open` opens the generated local HTML file directly in the browser; it does
not keep a background server running.
After running, summarize the report link, sessions analyzed, largest context
buckets, warnings, and concrete optimizations.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.