ox

A command-line tool for sharing team conventions, architecture decisions, and recorded coding sessions between AI coworkers in a repository.

In plain words
What is it for?
Use it to load repository guidance, start or stop session recording, inspect connection health, and initialize shared team context.
Why use it?
It keeps important project context available across sessions and teammates instead of relying on one conversation's memory.

Skill for Claude CodeCodex

Part of the ox plugin — 1 skill, 7 commands shipped together

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.

agentmods
npx agentmods add skills/sageox/ox/ox
Any agent
npx skills add sageox/ox --skill ox
Clone the repo
git clone --depth 1 https://github.com/sageox/ox

Made for: Claude Code, Codex.

Or install ox, the plugin that ships this one along with the rest of its 1 skill, 7 commands.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 821 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.00821
Opus 5 $0.00022 $0.00411
Sonnet 5 $0.00009 $0.00164
Haiku 4.5 $0.00004 $0.00082

Measured 3d ago against content hash 2bd096a6f370, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ox 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 3d 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-plugin/skills/ox/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SageOx (ox) - Team Context for AI Coworkers

ox is a CLI that gives AI coworkers shared team context: conventions, architectural decisions, session recording, and collaborative knowledge that persists across sessions and teammates.

When to Use

  • Starting work: Run ox agent prime to load team context (conventions, norms, decisions)
  • Recording sessions: ox agent session start / ox agent session stop to capture work to the project ledger
  • Checking health: ox status for auth/sync/daemon state, ox doctor for diagnostics
  • Initializing: ox init to set up SageOx in a new repository

Key Concepts

  • Team Context - shared conventions, norms, and architectural decisions (versioned)
  • Ledger - historical record of sessions, decisions, and discussions
  • Session - a recorded human-to-AI coworker conversation
  • AI Coworker - an AI participant on a team (not "agent" in user-facing output)

Essential Commands

Command Purpose
ox agent prime Load team context for this session
ox agent session start Begin recording a session
ox agent session stop Stop recording and push to ledger
ox status Check auth, sync, daemon health
ox doctor Run diagnostic checks
ox init Initialize SageOx in a repository
ox conventions Get verified team coding standards
ox session list List recent sessions from ledger

Searching Code, History, PRs

ox code queries the local CodeDB index (symbols, resolved call graph, diffs, git history, indexed PRs/issues/comments). Reach for it before grep/ripgrep on this repo.

Verb-mode (preferred — match on the intent verb):

Intent Command
Symbol definition ox code defs <name>
Who calls (resolved call graph) ox code callers <name>
What calls (transitive via --depth) ox code callees <name> --depth 2
Text references ox code refs <name> [--lang go]
Commits touching ox code log <path> [--author X] [--after YYYY-MM-DD]
PR triage (most stalled first) ox code prs --sort stalled
Recent GitHub activity ox code activity --since 7d
Hotspots & contention ox code insights
Index health ox code status

Read the full file on GitHub · 72 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. 3d ago First seen · 72 lines · 44 tokens per session scan A 2bd096a6f370

Subscribe to this mod's changes

ox is a skill published in the GitHub repository sageox/ox (50 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 821 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

excalidraw-diagram

Generate Excalidraw diagrams from text content. Supports three output modes - Obsidian (.md), Standard (.excalidraw), and Animated (.excalidraw with animation order). Triggers on "Excalidraw", "diagram", "standard excalidraw", "animate".

breferrari/obsidian-mind · 67 tokens

qmd

Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…

breferrari/obsidian-mind · 142 tokens

obsidian-cli

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…

breferrari/obsidian-mind · 102 tokens

unity-vrc-world-sdk-3

VRChat World SDK 3 guide for scene and Inspector setup, component placement, optimization, and upload. Use for VRChat world scene configuration, VRC SDK components, layers, baked lighting, Quest/Android performance, Dynamics for Worlds, Build Panel warning triage, validation, and upload. Covers VRCSceneDescriptor…

niaka3dayo/agent-skills-vrc-udon · 225 tokens

unity-vrc-skills-renovator

VRChat skill renovator for knowledge fill, refresh, and quality improvement. Use this skill when updating VRChat skills to new SDK versions, filling missing knowledge, fixing outdated information, or improving skill quality. Targets unity-vrc-udon-sharp and unity-vrc-world-sdk-3 skills. Triggers on: update skills, SDK…

niaka3dayo/agent-skills-vrc-udon · 101 tokens

neo4j-document-import-skill

Ingests unstructured and semi-structured documents into Neo4j as a knowledge graph. Use when chunking PDFs, HTML, plain text, or Markdown; extracting entities and relationships from text with an LLM (SimpleKGPipeline, neo4j-graphrag); loading JSON via apoc.load.json; building Document→Chunk→Entity graph structures; or…

neo4j-contrib/neo4j-skills · 187 tokens