ocx

A command-line control panel for a locally running opencodex proxy, which routes coding-agent requests to different AI providers. It covers accounts, providers, models, usage, costs, logs, access keys, and related management tasks.

In plain words
What is it for?
Use it to check available models, manage provider accounts and access keys, inspect requests and costs, and clean up stored proxy data.
Why use it?
It gives you one place to inspect and operate the proxy instead of managing its routing and usage details by hand.

Skill for Claude CodeCodex

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/lidge-jun/opencodex/ocx
Any agent
npx skills add lidge-jun/opencodex --skill ocx
Clone the repo
git clone --depth 1 https://github.com/lidge-jun/opencodex

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,446 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 $0.00000 $0.01446
Opus 5 $0.00000 $0.00723
Sonnet 5 $0.00000 $0.00289
Haiku 4.5 $0.00000 $0.00145

Measured 2d ago against content hash 8cae3e1ede53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ocx 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 2d 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.

skills/ocx/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operating ocx

ocx controls a locally running opencodex proxy. The CLI covers the dashboard's operational surface, with one consent exception (starring) recorded under Consent below. ocx capabilities lists the declared index, not every verb.

Be precise about the gap, because guessing costs you more than reading: the capability index below is complete and authoritative for what it lists, and it does not yet list every management route. A route with no declared capability may still have a working command — ocx access key and ocx route policy both work while capabilities --route returns nothing for them. So use the index first, and fall back to ocx <group> help before concluding a capability is missing.

This skill is for operating a proxy. Two neighbours cover different jobs: AGENTS_INSTALL.md is for installing one, and the repository AGENTS.md is for changing the codebase.

Start here

ocx capabilities --json

That is the machine-readable index of declared verbs, the routes they drive, their flags, and whether they mutate. Read it first rather than guessing a command name. It is not exhaustive — an unmatched --route exits 4 when the table has no row, even if a working verb exists. The converse of generation also holds: a verb can exist without appearing here (ocx access key, ocx route policy).

Narrow it when you already know what you want:

ocx capabilities --mutating-only --json      # only state-changing verbs
ocx capabilities --route /api/logs           # which verbs drive one route

An unmatched --route exits 4 rather than printing an empty success.

Three steps before any management call

  1. ocx ready --json — is the proxy up and admitting requests?
  2. ocx status --json — is this binary the same build as the running proxy? A version skew means the help and flags you just read describe a different build than the one answering.
  3. Then the real command, with --json.

Skipping step 2 is how an agent ends up reporting that a flag "does not work" when it simply does not exist in the running build yet.

Read the full file on GitHub · 121 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 121 lines · 0 tokens per session scan A 8cae3e1ede53

Subscribe to this mod's changes

ocx is a skill published in the GitHub repository lidge-jun/opencodex (12,853 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,446 tokens. 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

skill-creator

Create new OpenCode skills with the standard scaffold.

grahamton/merchGent · 14 tokens

behavioral-evals

Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests.

google-gemini/gemini-cli · 39 tokens

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

opencli-usage

Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".

jackwener/OpenCLI · 74 tokens

google-agents-cli-publish

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini Enterprise", "publish to Gemini Enterprise", or needs guidance on the agents-cli publish gemini-enterprise command. Also use when the user wants to "manage agents in Agent Registry"…

google/agents-cli · 141 tokens

google-agents-cli-scaffold

This skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add deployment", "enhance my project", or "upgrade my project". Part of the agents-cli skills suite. Covers agents-cli scaffold create, scaffold enhance, and…

google/agents-cli · 135 tokens