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 rocky2431/ultra-builder-pro --skill codex-collabgit clone --depth 1 https://github.com/rocky2431/ultra-builder-proWrote 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/rocky2431/ultra-builder-pro/codex-collab)<a href="https://agentmods.dev/skills/rocky2431/ultra-builder-pro/codex-collab"><img src="https://agentmods.dev/badge/skills/rocky2431/ultra-builder-pro/codex-collab.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.00805 |
| Opus 5 | $0.00036 | $0.00402 |
| Sonnet 5 | $0.00014 | $0.00161 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
codex-collab 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 8d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Collab - Dual AI Collaboration (OpenAI)
Use OpenAI's Codex CLI as an independent sub-agent within Claude Code. Claude orchestrates, Codex provides independent analysis powered by OpenAI models, Claude synthesizes the final result. All output goes through files — zero context pollution.
For code review specifically, use the official /codex:review plugin (or /codex:adversarial-review) directly — that's the dedicated, well-maintained path for the review use case. This skill covers the non-review collaboration modes the official plugin doesn't address.
Prerequisites
- Codex CLI installed:
npm install -g @openai/codex - Authenticated:
codex login - Verify:
codex --version
Usage
/codex-collab understand # Codex analyzes project structure
/codex-collab opinion <topic> # Get Codex's take on an architecture decision
/codex-collab compare <topic> # Both AIs answer independently, then synthesize
/codex-collab free <prompt> # Free-form prompt to Codex
When the user doesn't use a subcommand but mentions Codex in a collaborative way, infer the most appropriate mode from context. Never infer review — route review explicitly to /codex:review instead.
codex exec — Non-Interactive Mode
For understand/opinion/compare/free modes. Use -o (--output-last-message) to save clean output.
# Write mode (default)
codex exec "Your prompt here" --full-auto -o "${SESSION_PATH}/output.md" 2>"${SESSION_PATH}/error.log"
# Read-only analysis (no --full-auto, use -s read-only instead)
codex exec "Analyze this project" -s read-only -o "${SESSION_PATH}/output.md" 2>"${SESSION_PATH}/error.log"
Error Handling
- If
codexnot found:npm install -g @openai/codex - If auth fails:
codex login - If timeout (>5min): check partial output in file
- If empty output: proceed with Claude-only analysis
- Never block the workflow on Codex failure
Reference Files
Read these when you need details beyond what's in this SKILL.md:
What ships with it
5 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.
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.
- 8d ago First seen · 59 lines · 72 tokens per session scan A 1f17ae30981f
codex-collab is a skill published in the GitHub repository rocky2431/ultra-builder-pro (11 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 805 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…