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 Dong90/oh-my-taiyiforge --skill taiyi-ultraworkgit clone --depth 1 https://github.com/Dong90/oh-my-taiyiforgeWrote 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/dong90/oh-my-taiyiforge/taiyi-ultrawork)<a href="https://agentmods.dev/skills/dong90/oh-my-taiyiforge/taiyi-ultrawork"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-ultrawork/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/dong90/oh-my-taiyiforge/taiyi-ultrawork"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-ultrawork.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 | $0.00039 | $0.00460 |
| Opus 5.5 | $0.00016 | $0.00184 |
| Sonnet 5.5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
taiyi-ultrawork 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 1mo 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.
What it actually says
taiyi-ultrawork
加载时机：/taiyi:ultrawork · 关键词 ulw · scripts/taiyi-forge.sh ultrawork · ultrawork step 输出。
强制契约（TAIYI_ULW_AUTO_TASK=1 或 step 标明 AUTO）
- 主会话 禁止 亲自实现全部 TASK 切片。
- 对
step输出的每个 worker 并行 调用 CursorTask工具（或 Claude subagent）。 - 每个 worker prompt 须含：
/taiyi:agent <role>· 切片任务 ·/taiyi:sp test-driven-development· 完成标准 ralph 绿。 - 文件所有权清单：每个 worker prompt 必须附带其 write_files 清单 + 锁定表，标明：
- 该 worker 拥有 的文件（独占写权限）
- 该 worker 不可触碰 的文件（属其他 worker）
- 违反此规定 → 合并冲突，worker 需 rebase 重试
- 全部 worker 返回后：主会话合并冲突（如有）→
scripts/taiyi-forge.sh ralph→/taiyi:continue。 - 停止：
/taiyi:stop-mode。
辅助 Skill
/taiyi:sp dispatching-parallel-agents/taiyi:sp subagent-driven-development
引擎
scripts/taiyi-forge.sh step [slug] --mode ultrawork
环境变量：
| 变量 | 说明 |
|---|---|
TAIYI_ULW_TASK=0 |
不打印 Task 示例 |
TAIYI_ULW_AUTO_TASK=1 |
step 输出强制 AUTO 派发契约 |
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.
- 1mo ago First seen · 39 lines · 39 tokens per session scan A 8e46a79d2a9c
taiyi-ultrawork is a skill published in the GitHub repository Dong90/oh-my-taiyiforge (859 stars, last pushed 16d ago), licensed MIT. It adds 39 tokens to every session and 460 once invoked, about $0.0002 per session on Opus 5.5. 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
business-requirements
Read and hand-edit the app's business requirements — the checklist the harness verifies the built app against. MUST be loaded whenever the user asks to add, change, remove, reword, re-prioritise, or reclassify a business requirement (e.g. "add a requirement that…", "that rule is wrong, fix it", "drop the requirement…
first-run-open
Owns the opening move of first-run when the user has NOT handed you a substantive prompt (cold start), and sets the voice-vs-text opening posture for any open. Shows a provisional dream and a guess about who the user is, then learns from their correction (show-to-learn) and re-aims. Hands back to the first-run spine…
disqualification
The honest exit. Loads when qualification signals sustained-low or a realism failure (the ask is genuinely outside QB's wheelhouse). Acknowledges the mismatch plainly, suggests a realistic alternative, preserves dignity, and does not chase. A legitimate designed outcome, not a framework failure.
qualification
Reads qualification signals from the user's input and passive context, sets the archetype and effort mode, and decides whether to proceed up the convince ladder or route to the disqualification skill. Runs alongside the first-run spine from the first substantive message onward. Falls back to "proceed at normal effort"…
build-recovery
Owns the build wait and build failure. Narrates the generation honestly while it runs, and when it errors, names the failure plainly with a real recovery path instead of a generic "oops". Loads when generation is long or returns an error. The single highest-risk moment for the "it's actually building" belief.
chat-formatting-widgets
Governs the custom markdown widgets rendered in the QuantumByte chat interface. This includes the inline highlight-mark span (use on every question the user must answer). You must check this skill on every reply to format highlights.