Borrowing it
Nothing to install: this file belongs to radumarias/xorio-claude-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/radumarias/xorio-claude-plugin/main/CLAUDE.mdgit clone --depth 1 https://github.com/radumarias/xorio-claude-pluginWrote 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/instructions/radumarias/xorio-claude-plugin/claude-md)<a href="https://agentmods.dev/instructions/radumarias/xorio-claude-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/radumarias/xorio-claude-plugin/claude-md/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/instructions/radumarias/xorio-claude-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/radumarias/xorio-claude-plugin/claude-md.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 | $0.04241 | $0.04241 |
| Opus 5.5 | $0.01696 | $0.01696 |
| Sonnet 5.5 | $0.00848 | $0.00848 |
| Haiku 4.5 | $0.00424 | $0.00424 |
Grade D, and why
xorio-claude-plugin CLAUDE.md scanned grade D with 2 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 6d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- `PreToolUse(Bash|Read|Grep)` — runs `hooks/block-secret-file-reads.mjs` (invoked as `node ${CLAUDE_PLUGIN_ROOT}/hooks/...`), a deny-only guard for reading secret / private-data files (`.env`, `.secrets`, key/cert files Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
On a personal machine the Read vector is normally handled by a declarative `permissions.deny` in `~/.claude/settings.json`, but **a plugin cannot ship permission rules** — a plugin's `settings.json` only honors `agent` / How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
A Claude Code plugin (xorio) providing development workflows: test generation, code cleanup, polishing, review, security auditing, and commit message creation. Supports Rust, TypeScript, and Python projects, with framework-specific standards for egui, React, Vue.js, Three.js, SparkJS, Docker, and AWS.
Plugin Architecture
.claude-plugin/plugin.json ← plugin manifest (name, version, metadata)
.claude-plugin/marketplace.json ← marketplace manifest: xorio (source ./) + the mods under mods/ (repo self-installs via /plugin marketplace add)
agents/ ← autonomous subagents (launched via Task tool)
commands/ ← slash commands (/xorio:tests, /xorio:polish, etc.)
hooks/ ← hooks.json (SessionStart context injection + PreToolUse secret-file guard) + block-secret-file-reads.mjs
mods/ ← separate plugins built on the function-hooks API (mods), each its own marketplace entry
rules/ ← injected context: design principles (planning.md), tool usage guide (tools.md)
skills/ ← skill workflows (SKILL.md + references/ for standards)
The repo doubles as a marketplace: marketplace.json lets users /plugin marketplace add radumarias/xorio-claude-plugin then /plugin install xorio@xorio, and optionally /plugin install doc-preview@xorio. For local development use --plugin-dir instead (see Installation for Development).
Component Relationships
The /xorio:tests command is the primary workflow entry point. It orchestrates:
- Language/framework detection from file extensions and dependency files
- Loading matching standards from
skills/tests/references/test-standards-{lang}.md - Launching
test-analyzeragent (analysis only, no writes) - Optionally launching
test-docs-advisoragent in parallel (read-only) - User selects which gaps to fill
- Launching
test-generatoragent(s) (one per language, writes tests)
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.
- 6d ago Changed · +99 tokens per session 145c09350ced
- 11d ago Changed · +70 tokens per session 68e963158ea6
- 20d ago Changed · +20 lines · +814 tokens per session d41b6419f799
- 1mo ago First seen · 144 lines · 3,258 tokens per session scan D d441e676878d
xorio-claude-plugin CLAUDE.md is an instructions file published in the GitHub repository radumarias/xorio-claude-plugin (3 stars, last pushed 6d ago), licensed MIT. It adds 4,241 tokens to every session, about $0.0170 per session on Opus 5.5. A static security scan graded it D with 2 findings (reaches for credential files, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.