ultra-mode

ultra-mode is a skill for Codex from xz1220/open-dynamic-workflows. It costs 127 tokens per session (1,732 once invoked), scanned A, original, MIT.

A working mode for explicitly authorized, exhaustive coding-agent tasks that may use multiple independent agents or background workflows. It is a behavior setting, not a particular tool.

In plain words
What is it for?
Use it for requests that explicitly ask for exhaustive work, parallel agents, multi-pass review, or independent verification within a defined scope.
Why use it?
It helps the agent spend more effort on completeness and independent checking when the request calls for it, while keeping ordinary small tasks appropriately small.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents.

Good fit Use it for requests that explicitly ask for exhaustive work, parallel agents, multi-pass review, or independent verification within a defined scope.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xz1220/open-dynamic-workflows/ultra-mode
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 xz1220/open-dynamic-workflows --skill ultra-mode
Clone the repo
git clone --depth 1 https://github.com/xz1220/open-dynamic-workflows

Made for: Codex.

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.

agentmods badge for ultra-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/xz1220/open-dynamic-workflows/ultra-mode/github.svg)](https://agentmods.dev/skills/xz1220/open-dynamic-workflows/ultra-mode)
Your own site
<a href="https://agentmods.dev/skills/xz1220/open-dynamic-workflows/ultra-mode"><img src="https://agentmods.dev/badge/skills/xz1220/open-dynamic-workflows/ultra-mode/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.

agentmods 80×15 button for ultra-mode

Your own site · 80×15
<a href="https://agentmods.dev/skills/xz1220/open-dynamic-workflows/ultra-mode"><img src="https://agentmods.dev/badge/skills/xz1220/open-dynamic-workflows/ultra-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,732 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00127 $0.01732
Opus 5 $0.00063 $0.00866
Sonnet 5 $0.00025 $0.00346
Haiku 4.5 $0.00013 $0.00173

Measured 9d ago against content hash d5874bebecb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ultra-mode 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/ultra-mode-workflow.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/ultra-mode/SKILL.md · 164 lines

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.

Ultracode / Ultra Mode

Ultracode is a behavioral mode, not a specific tool. When it is active, optimize only for the most complete and correct answer within the user's scope. Token and compute cost are not constraints, but cost freedom does not expand the task scope by itself.

Use whatever independent-work mechanism the environment provides. In this repository, prefer Open Dynamic Workflows (odw). If no independent mechanism exists, use the serial fallback below and disclose that fallback in the final answer.

Scope Discipline

  • Treat activation as explicit authorization only. Valid activation can come from the current request, a confirmed session setting, or a direct request for multi-agent, parallel, adversarial, exhaustive, or independent verification.
  • Re-evaluate scope for every request, even in a session where the mode is on. Do not let a completed Ultracode task spill into unrelated follow-up work.
  • Keep trivial work trivial. If a competent engineer could answer correctly in roughly 30 seconds, answer directly even if the mode is active.
  • Match depth to the request. Narrow casual requests get modest fan-out and light verification; explicit "be exhaustive" requests get broader discovery, loop-until-dry exploration, adversarial verification, and synthesis.
  • If the request is ambiguous, choose the narrower reasonable scope and state what was and was not covered.
  • Add workers or rounds only to close a concrete coverage gap. "Budget remains" is not a reason by itself; "area X is unexamined" is.

Pick The Decomposition Purpose

Before dispatching work, decide which purpose the split serves:

  • Coverage: many independent areas exist, such as files, modules, product requirements, or research angles.
  • Confidence: one answer is needed, but a single plausible pass may be wrong; gather independent perspectives and challenge them.
  • Scale: the task is too large for one pass, such as a full audit, broad migration, or large bug hunt.

Read the full file on GitHub · 164 lines

Files

What ships with it

3 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. 9d ago First seen · 164 lines · 127 tokens per session scan A d5874bebecb5

Subscribe to this mod's changes

ultra-mode is a skill published in the GitHub repository xz1220/open-dynamic-workflows (101 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 1,732 once invoked, about $0.0006 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