MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
执行被显式授权的 Ultracode / Ultra Mode 请求：在用户给定范围内，把优化目标设为尽可能 详尽和正确，使用当前环境提供的任何独立工作机制（ODW workflow、子智能体、派发 worker、 并行工具任务）进行覆盖、验证和综合；只有完全没有这类机制时才使用串行多趟退化方案。
Install Ultra Mode
$ npx skills add xz1220/open-dynamic-workflows --skill ultra-mode -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install xz1220/open-dynamic-workflows ultra-mode --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/xz1220/open-dynamic-workflows.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ultra-mode/zh-CN .claude/skills/ultra-mode && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ultra-mode" agent skill from https://github.com/xz1220/open-dynamic-workflows/tree/main/skills/ultra-mode/zh-CN into .claude/skills/ultra-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultra-mode", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/xz1220/open-dynamic-workflows/tree/main/skills/ultra-mode/zh-CNType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add xz1220/open-dynamic-workflows --skill ultra-mode -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install xz1220/open-dynamic-workflows ultra-mode --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xz1220/open-dynamic-workflows.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ultra-mode/zh-CN .agents/skills/ultra-mode && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ultra-mode" agent skill from https://github.com/xz1220/open-dynamic-workflows/tree/main/skills/ultra-mode/zh-CN into .agents/skills/ultra-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultra-mode", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xz1220/open-dynamic-workflows --skill ultra-mode -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install xz1220/open-dynamic-workflows ultra-mode --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xz1220/open-dynamic-workflows.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ultra-mode/zh-CN .cursor/skills/ultra-mode && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ultra-mode" agent skill from https://github.com/xz1220/open-dynamic-workflows/tree/main/skills/ultra-mode/zh-CN into .cursor/skills/ultra-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultra-mode", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/xz1220/open-dynamic-workflows.git --path skills/ultra-mode/zh-CN--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add xz1220/open-dynamic-workflows --skill ultra-mode -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install xz1220/open-dynamic-workflows ultra-mode --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xz1220/open-dynamic-workflows.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ultra-mode/zh-CN .gemini/skills/ultra-mode && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ultra-mode" agent skill from https://github.com/xz1220/open-dynamic-workflows/tree/main/skills/ultra-mode/zh-CN into .gemini/skills/ultra-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultra-mode", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install xz1220/open-dynamic-workflows ultra-modeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add xz1220/open-dynamic-workflows --skill ultra-mode -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/xz1220/open-dynamic-workflows.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ultra-mode/zh-CN .github/skills/ultra-mode && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ultra-mode" agent skill from https://github.com/xz1220/open-dynamic-workflows/tree/main/skills/ultra-mode/zh-CN into .github/skills/ultra-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultra-mode", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xz1220/open-dynamic-workflows --skill ultra-mode -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install xz1220/open-dynamic-workflows ultra-mode --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xz1220/open-dynamic-workflows.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ultra-mode/zh-CN .opencode/skills/ultra-mode && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ultra-mode" agent skill from https://github.com/xz1220/open-dynamic-workflows/tree/main/skills/ultra-mode/zh-CN into .opencode/skills/ultra-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ultra-mode", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ultra-mode- GitHub stars
- 106
- Token cost
- ~832 tokens
- SKILL.md length
- 174 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
执行被显式授权的 Ultracode / Ultra Mode 请求：在用户给定范围内，把优化目标设为尽可能 详尽和正确，使用当前环境提供的任何独立工作机制（ODW workflow、子智能体、派发 worker、 并行工具任务）进行覆盖、验证和综合；只有完全没有这类机制时才使用串行多趟退化方案。
- Works in 5 steps: 先检查 odw --version。 → 在本仓库里，常规“规划者 -> 多分支 -> 评审者 -> 综合”用… → 离开本仓库时，读取… → …
- Agent Workflows work in your project
- SKILL.md covers 范围纪律, 先判断拆解目的, 控制流形态 and 质量门, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Ultra Mode is an agent skill from xz1220/open-dynamic-workflows. 执行被显式授权的 Ultracode / Ultra Mode 请求：在用户给定范围内，把优化目标设为尽可能 详尽和正确，使用当前环境提供的任何独立工作机制（ODW workflow、子智能体、派发 worker、 并行工具任务）进行覆盖、验证和综合；只有完全没有这类机制时才使用串行多趟退化方案。 当用户明确说 ultracode、ultra mode、go exhaustive、深度模式、多 agent、并行、 对抗式、彻底处理、别漏掉任何东西、每个角度都查一遍，或要求多种独立验证策略时使用。 不要只因为任务困难、技术性强、含糊或高风险就自行启用。
Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. The repository describes itself as: Open Dynamic Workflows: TypeScript CLI runtime for Claude Code-style dynamic workflows across Codex, Claude Code, Gemini, Qwen, Kimi, and custom coding-agent CLIs. The licence is MIT.
When your agent uses it
- Agent Workflows work in your project
Example prompts
- “/ultra-mode”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 先检查 odw --version。
- 在本仓库里，常规“规划者 -> 多分支 -> 评审者 -> 综合”用 examples/ultra-mode.js。
- 离开本仓库时，读取 ../references/ultra-mode-workflow.js，写入临时或项目本地 workflow，
- 如果任务需要挖到干为止、自定义领域 fan-out 或 pipeline，不要硬塞进内置模板；
- 检查返回的 final、lanes、reviews，把它们视为辅助素材。真实编辑、测试、提交和最终判断
What it can do on your machine
Read from SKILL.md and the folder at commit 16f57ee. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Ultra Mode loads about 832 tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 174 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from xz1220/open-dynamic-workflows at commit 16f57ee, republished under its MIT licence (© xz1220). 174 words, ~832 tokens.
Download SKILL.mdSave it as
.claude/skills/ultra-mode/SKILL.md (or your agent's skills folder).- name
- ultra-mode
- description
- 执行被显式授权的 Ultracode / Ultra Mode 请求：在用户给定范围内，把优化目标设为尽可能 详尽和正确，使用当前环境提供的任何独立工作机制（ODW workflow、子智能体、派发 worker、 并行工具任务）进行覆盖、验证和综合；只有完全没有这类机制时才使用串行多趟退化方案。 当用户明确说 ultracode、ultra mode、go exhaustive、深度模式、多 agent、并行、 对抗式、彻底处理、别漏掉任何东西、每个角度都查一遍，或要求多种独立验证策略时使用。 不要只因为任务困难、技术性强、含糊或高风险就自行启用。
Ultracode / Ultra Mode
Ultracode 是一种行为模式，不绑定某个具体工具。激活后，只在用户给定范围内优化一件事：产出尽可能完整、正确的答案。Token 和算力成本不是约束，但这不等于可以扩大任务范围。
使用环境里任何可用的独立工作机制。本仓库里优先使用 Open Dynamic Workflows (odw)。如果完全没有独立 worker 能力，就使用本文末尾的串行退化方案，并在最终回答里说明。
范围纪律
- 只把显式授权视为激活依据：当前请求点名、已确认的 session 设置，或用户直接要求多 agent、 并行、对抗式、穷尽式、独立验证。
- 即使 session 级别已经开启，也要逐个请求重新评估范围。一个 Ultracode 任务完成后， 不要让它蔓延到无关后续请求。
- 小事仍然小做。合格工程师 30 秒内能答对的请求，直接回答，不上编排。
- 深度要和请求匹配。窄而随意的请求只需要适中分头查找和轻量验证；明确要求彻底性的请求才使用 更大规模的发现、挖到干为止、对抗式验证和综合。
- 遇到含糊范围，按较窄的合理范围做，并说明覆盖了什么、没覆盖什么。
- 每新增 worker 或轮次，都要对应一个具体覆盖缺口。仅仅“预算还有”不是理由；“某个领域未检查”才是理由。
先判断拆解目的
派发工作前，先判断拆解是为了什么：
- 全面覆盖：存在很多独立部分，例如文件、模块、需求项、研究角度。
- 信心/确定性：只需要一个答案，但单次尝试可能听着合理却是错的，需要独立视角和反驳。
- 规模：任务大到一次做不完，例如完整审计、大迁移、大范围排查。
真实 Ultracode 任务通常同时包含至少两类目的。
控制流形态
先问：某个 worker 的结果能不能立刻被用上，还是必须等所有同级结果都回来？
- Fan-out / fan-in：把独立单元派发出去，再在屏障处汇总。只在下一步确实需要全量结果时使用： 去重、排名、判断“到底有没有问题”、最终综合。
- Pipeline：让每个条目按自己的节奏走完多个阶段，不等待无关条目。多阶段工作默认用这个形态， 例如发现 -> 验证 -> 撰写。
- 挖到干为止：开放式排查时，跑一轮独立查找、合并去重、再跑下一轮，直到连续 2-3 轮没有新发现 才停；高风险审计可以提高阈值。
- 预算感知扩展：用户给了明确精力或 token 预算时，持续扩大覆盖和验证深度，直到预算接近耗尽， 或确实没有具体缺口。
典型审计形态：按领域 fan-out；每个领域内部 loop-until-dry；每个存活发现进入独立验证 pipeline； 最后只保留一次屏障，做去重综合。
质量门
- 对抗式验证：非平凡发现或“已修复”结论，都要派怀疑者尝试反驳。举证责任在提出结论的一方。 多数认真反驳仍反驳不倒时，才保留该发现。
- 多视角验证：把怀疑者分配到不同失败模式：需求正确性、安全性、性能/资源、实际复现、 边界情况、未检查假设。
- 评审团模式：开放式设计或综合题，先让几个真正不同的方案独立产生，再由独立评委打分， 最终以最强方案为基础，并吸收其他方案的好点子。
- 多策略搜索：探索类任务用不同搜索策略并行查找，避免单一策略的盲区定义结果。
- 查漏评审：以为完成后，专门跑一趟“还漏了什么”：未打开文件、未验证断言、未读资料、 未测边界、未覆盖角度。真实缺口要重新纳入工作，而不是当备注。
- 覆盖披露：如果覆盖被限定过，最终回答里要具体说明，例如只抽样、只看 top N、某检查未重试。
映射到 ODW
odw 可用时优先使用它承载独立工作。
- 先检查
odw --version。 - 在本仓库里，常规“规划者 -> 多分支 -> 评审者 -> 综合”用
examples/ultra-mode.js。 - 离开本仓库时，读取
../references/ultra-mode-workflow.js，写入临时或项目本地 workflow， 例如.odw/workflows/ultra-mode.js。 - 如果任务需要挖到干为止、自定义领域 fan-out 或 pipeline，不要硬塞进内置模板； 写一个任务专用 ODW workflow。
- 检查返回的
final、lanes、reviews，把它们视为辅助素材。真实编辑、测试、提交和最终判断 仍由你完成。
有边界的运行：
odw run examples/ultra-mode.js --wait --args '{"task":"<任务>","intensity":"standard"}'较长运行：
RUN=$(odw run examples/ultra-mode.js --args '{"task":"<任务>","intensity":"max"}')
odw logs "$RUN" --follow
odw result "$RUN"常用参数：
task：必填，除非直接传入裸字符串。intensity：lite、standard或max；默认standard。lanes：独立工作分支数量；默认按强度分别为 3/4/6。reviewers：对抗式评审者数量；默认按强度分别为 2/3/4。constraints：硬性要求，可以是字符串或字符串数组。context：相关文件、仓库事实、已有发现或用户偏好。finalFormat：最终综合结果的格式要求。
ultra-mode 的 lane 显式请求隔离（isolation: "worktree"），改动落在一次性 git worktree 里——请保持这一点，除非用户明确要求共享的就地执行（ODW 的默认行为）并接受风险。worktree 隔离要求 source 是有提交的 git 仓库。意外变大的运行用
odw stop <run_id> 停止，或用 odw pause <run_id> 暂停。
串行退化方案
如果没有任何独立 worker 能力，就有意识地模拟结构：
- 先写出拆解方案：切片、视角、领域。
- 把每个切片当成独立处理，不让前面切片的结论污染后面切片。
- 把验证作为独立趟处理，切换到怀疑者视角。
- 显式重复发现轮次，直到某轮没有新发现，或明确预算接近耗尽。
- 最终回答里说明覆盖和验证是串行多趟模拟完成的，不是独立并行 worker 完成的。
最终责任
worker 输出只是素材，不是成品。你必须读完、裁决分歧、去重重叠发现、判断什么是真的， 再综合成一份连贯答案。不要只罗列“worker 1 说 X、worker 2 说 Y”。
© xz1220, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/ultra-mode/zh-CN of xz1220/open-dynamic-workflows.
Open the folder on GitHubat commit 16f57ee
Compare with similar skills
Ultra Mode next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ultra Mode this skillxz1220/open-dynamic-workflows | 106 | — | ~832 | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 36 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 796 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
- Official
Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
More from xz1220/open-dynamic-workflows
Open Dynamic Workflows
xz1220/open-dynamic-workflows
Write and run dynamic workflows: short JavaScript scripts in Claude Code's workflow dialect, run with the odw CLI outside the host agent's context, fanning subtasks out to coding-agent CLIs (Codex…
Ultra Mode
xz1220/open-dynamic-workflows
Execute explicitly authorized Ultracode / Ultra Mode requests: optimize for exhaustive, correct answers within the user's stated scope by using any available independent-work mechanism (ODW…
Open Dynamic Workflows
xz1220/open-dynamic-workflows
编写并运行 dynamic workflow：用 Claude Code 的 workflow 方言写一段简短的 JavaScript 脚本，再用 odw CLI 在宿主 agent 的上下文之外，把子任务扇出给 coding-agent CLI （Codex、Claude Code、Gemini、Qwen、Kimi 或自定义），后台跑完后只取回最终结果。
Related
Categories
Questions about Ultra Mode
What does Ultra Mode do?
执行被显式授权的 Ultracode / Ultra Mode 请求：在用户给定范围内，把优化目标设为尽可能 详尽和正确，使用当前环境提供的任何独立工作机制（ODW workflow、子智能体、派发 worker、 并行工具任务）进行覆盖、验证和综合；只有完全没有这类机制时才使用串行多趟退化方案。. Ultra Mode is an agent skill from xz1220/open-dynamic-workflows.
When should I use Ultra Mode?
Ultra Mode fits situations like: agent Workflows work in your project.
How do I install Ultra Mode in Claude Code?
Run `npx skills add xz1220/open-dynamic-workflows --skill ultra-mode -a claude-code`. Or copy the skill folder (skills/ultra-mode/zh-CN in xz1220/open-dynamic-workflows) into .claude/skills/ultra-mode in your project. Claude Code loads it when a task matches its description.
How do I install Ultra Mode in Codex?
Run `npx skills add xz1220/open-dynamic-workflows --skill ultra-mode -a codex`. Or copy the skill folder (skills/ultra-mode/zh-CN in xz1220/open-dynamic-workflows) into .agents/skills/ultra-mode in your project. Codex loads it when a task matches its description.
Can I use Ultra Mode in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xz1220/open-dynamic-workflows --skill ultra-mode -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ultra-mode, .gemini/skills/ultra-mode, .github/skills/ultra-mode and .opencode/skills/ultra-mode in your project.
What does Ultra Mode need to run?
SKILL.md names no scripts, command-line tools or credentials: Ultra Mode is instructions for the agent only.
Does Ultra Mode access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Ultra Mode safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Ultra Mode use?
Ultra Mode is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ultra Mode use?
About 832 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Ultra Mode?
Skills that share tags, products or a category with Ultra Mode: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ultra Mode?
xz1220 (a GitHub user) maintains it in xz1220/open-dynamic-workflows, which has 106 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 7, 2026.
Source: xz1220/open-dynamic-workflows on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.