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 xz1220/open-dynamic-workflows --skill ultra-modegit clone --depth 1 https://github.com/xz1220/open-dynamic-workflowsWrote 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/xz1220/open-dynamic-workflows/ultra-mode)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00127 | $0.01732 |
| Opus 5 | $0.00063 | $0.00866 |
| Sonnet 5 | $0.00025 | $0.00346 |
| Haiku 4.5 | $0.00013 | $0.00173 |
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.
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 — 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.
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.
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.
- 9d ago First seen · 164 lines · 127 tokens per session scan A d5874bebecb5
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.
Other skills, from other repositories
create-plugin
Use when authoring a new octomux plugin package — package layout, the apply(ctx) export, choosing a registrar, shipping kind presets, testing locally, and confirming with octomux doctor.
review-deep
Drive the deep-review phase of an automated PR review. Consumes the walkthrough, runs the deterministic deep-review workflow (parallel lenses → adversarial validation → code-enforced threshold/caps), drafts the surviving findings, and completes the review run.
add-plugin
Use when installing, disabling, enabling, or troubleshooting a third-party octomux plugin — the manifest row shape, octomux plugins list/disable/enable, reading octomux doctor output, and recovering a broken boot with --safe-mode.
create-task
Use when creating an octomux task to dispatch autonomous Claude Code agents for building features, fixing bugs, or any code changes.
review-orchestrator
Drive an automated PR review. Produces a structured walkthrough plus inline draft comments via the octomux review CLI. NEVER posts to GitHub directly — publishing is human-gated.
plan
Deep planning for a specific Jira ticket — codebase deep-dive, interview on ambiguous points, update ticket with detailed approach. Use before implementing large or unclear tickets. Usage - /plan IN-XXX.