A multi-agent orchestration skill that coordinates several OpenAI Codex agents to work on one coding task. It divides broad work among agents and combines their findings or changes.

Running exhaustive audits, parallel code reviews, finding issues across a project, verifying results, and implementing complex changes with up to ten concurrent agents.

It helps handle large reviews, migrations, and investigations by assigning focused parts of the work to multiple agents at once.

ultracodex — Skill for Claude Code and Codex by southlab-ai

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.

Any agent

npx skills add southlab-ai/Claude-Plugin-Marketplace --skill ultracodex

Clone the repo

git clone --depth 1 https://github.com/southlab-ai/Claude-Plugin-Marketplace

Made for: Claude Code, Codex.

Or install ultracodex, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/ultracodex/github.svg)](https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/ultracodex)

Your own site

<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/ultracodex"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/ultracodex/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/ultracodex"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/ultracodex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,837 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00107	$0.01837
Opus 5	$0.00053	$0.00919
Sonnet 5	$0.00021	$0.00367
Haiku 4.5	$0.00011	$0.00184

Measured 12d ago against content hash 2e0a53c67fd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ultracodex 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 12d 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.

plugins/ultracodex/skills/ultracodex/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ultracodex — Codex fleet orchestration

You (Claude) are the orchestrator: decompose, write prompts, spawn, synthesize, decide the next phase. The workers are codex exec processes (see [[codex-agent]] skill for base conventions). Token cost on the Codex side is billed to the user's own Codex plan and is not your concern — but the concurrency cap is.

Model & effort per role (GPT-5.6 family)

Model	Tier	Fleet roles
`gpt-5.6-luna`	fast	mechanical, well-scoped: extraction, classification, per-file smoke checks
`gpt-5.6-terra`	workhorse — default	finders, reviewers, 1-vote verifiers, straightforward implementers
`gpt-5.6-sol`	flagship	judges, adversarial verifiers on high-severity findings, design proposals, complex implementers

Default: gpt-5.6-terra at effort medium unless the table or the user says otherwise.
Effort values on 5.6: low | medium | high | xhigh | max (max is new to 5.6; minimal is gone).
Escalate per-agent — sol and/or high/xhigh — when the user asks ("xhigh", "a fondo", "exhaustivo") or the role sits in sol's row. Reserve max for a single hardest problem (one stuck bug, one judge on a critical design), never fleet-wide: 10 agents at max is the slowest possible run.
Legacy gpt-5.5 still works; use it only if the user names it.
State in your plan paragraph which model+effort each phase uses.

Hard limits

Max 10 Codex agents running concurrently. Before spawning, count your running background tasks; if 10 are live, wait for notifications and backfill as slots free up.
Max ~30 agents per full run unless the user asks for more. log what you're skipping if you bound coverage — no silent truncation.

Run layout

/tmp/ultracodex/<run-slug>/
  plan.md                      # your decomposition, updated per phase
  <phase>/<agent-slug>/
    prompt.md                  # full self-contained prompt
    schema.json                # optional JSON Schema for structured output
    last-message.md            # agent's final answer (-o)

Read the full file on GitHub · 95 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.

12d ago First seen · 95 lines · 107 tokens per session scan A 2e0a53c67fd9

Subscribe to this mod's changes

ultracodex is a skill published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 1,837 once invoked, about $0.0005 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 2026-08-31.

Building agents Claude Code Multi-Agent ai-agents computer-vision marketplace mcp

cosmergon

Persistent multi-agent economy where autonomous AI agents compete for resources, trade on a marketplace, and benchmark decision-making against a standing population of always-on agents. Invite other agents for energy rewards. Auto-registers — no API key needed.

rkocosmergon/cosmergon-agent · 50 tokens

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

browser_cdp

A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.

mateaix/mateclaw · 44 tokens

flow-next-tracker-sync

Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.

gmickel/flow-next · 44 tokens