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-diagram-flowgit 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-diagram-flow)<a href="https://agentmods.dev/skills/dong90/oh-my-taiyiforge/taiyi-diagram-flow"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-diagram-flow/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-diagram-flow"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-diagram-flow.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 | $0.00044 | $0.01213 |
| Opus 5.5 | $0.00018 | $0.00485 |
| Sonnet 5.5 | $0.00009 | $0.00243 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
taiyi-diagram-flow 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
taiyi-diagram-flow
目的
把需求里的用户路径、阶段门禁、错误分支、状态迁移画成可执行的流程图——供 TASK.md 切片、taiyi-dev 实现与 taiyi-test 用例一一对应。
何时使用
| 时机 | 说明 |
|---|---|
taiyi-design 有复杂分支/异步 |
主流程 + 异常流 |
taiyi-task 拆切片前 |
每切片应对齐流程中的一段 |
| 九阶段 / harness / 门禁说明 | 工作流全景 flowchart |
taiyi-test 写 E2E 场景 |
Given/When/Then → 路径覆盖 |
可跳过：线性 CRUD、无分支、AC 已表格化且无歧义。
输入
REQUIREMENT.md（User Stories、AC）DESIGN.md（状态、API、错误码）TASK.md（若补画 dev 级细节）- （可选）
docs/taiyi/workflow-manifest.yaml（官方九阶段顺序）
输出
| 产物 | 路径 |
|---|---|
| 主流程图 | .taiyi/changes/<slug>/diagrams/flows.md |
| 子流程 | .taiyi/changes/<slug>/diagrams/flow-<name>.md |
| 嵌入 | REQUIREMENT.md / TASK.md / TEST.md 内 mermaid 块 |
mark-aux：scripts/taiyi-forge.sh mark-aux <slug> taiyi-diagram-flow（当 diagrams/flows.md 或子文件已写入实质内容）。
图类型选型
| 场景 | Mermaid 类型 |
|---|---|
| 用户/业务步骤 | flowchart TD 或 flowchart LR |
| API / 模块调用时序 | sequenceDiagram |
| 订单/任务/变更状态 | stateDiagram-v2 |
| 并行网关 | flowchart + fork 节点说明 |
| 九阶段推进 | flowchart LR + subgraph 阶段 |
执行步骤
- 从 AC 提取路径：每条 AC 至少对应图中一条从入口到终态的路径
- 标门禁节点：人工门（change/design/review）、quality gate、delivery gate 用 菱形
{ }或[门禁: …] - 标失败边：每个决策点须有 否 分支（回退、重试、abort）——禁止只画 happy path
- 写 flows.md：
# Flow Diagrams: <slug>
## Main user flow
\`\`\`mermaid
flowchart TD
A[用户提交] --> B{校验}
B -->|通过| C[写入]
B -->|失败| D[4xx + 消息]
C --> E[完成]
\`\`\`
## Taiyi 九阶段（本变更）
\`\`\`mermaid
flowchart LR
change --> requirement --> design --> task --> dev --> test --> review --> integration
\`\`\`
## Traceability
| 节点 | AC / TASK |
|------|-----------|
| B | AC-2 |
| C | TASK-1 |
- （可选）导出 PNG：
node scripts/render-mermaid.mjs diagrams/flows.md - 回链 TASK.md：每个切片标题旁注
(flow: Main user flow → C) - mark-aux
命名与风格
- 节点 ID：
camelCase或snake_case，全文件唯一 - 用户可见文案用中文；内部模块用代码名（
workflow-engine） - 单图节点 ≤15；超出拆
flow-<topic>.md并在 flows.md 链过去 - 颜色（可选）：
classDef gate fill:#fef3c7标注门禁
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 · 115 lines · 44 tokens per session scan A 004efd9ae5c7
taiyi-diagram-flow is a skill published in the GitHub repository Dong90/oh-my-taiyiforge (859 stars, last pushed 16d ago), licensed MIT. It adds 44 tokens to every session and 1,213 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.