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-devgit 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-dev)<a href="https://agentmods.dev/skills/dong90/oh-my-taiyiforge/taiyi-dev"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-dev/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-dev"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 17 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 201 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 168 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 171 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 230 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 232 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00021 | $0.03188 |
| Opus 5 | $0.00010 | $0.01594 |
| Sonnet 5 | $0.00004 | $0.00638 |
| Haiku 4.5 | $0.00002 | $0.00319 |
Grade A, and why
taiyi-dev 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 11d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
taiyi-dev — TDD 开发
进入本阶段前请优先读
.taiyi/changes/<slug>/PHASE-CONTEXT.md（~500 tokens），不要全量加载上游工件。
框架集成
本阶段使用以下框架：
| 框架 | 用途 | 何时加载 |
|---|---|---|
| Harness | 阶段门禁与推进（apply 清单 · status → continue；legacy：npx taiyi apply/complete） |
全程 |
| Superpowers | test-driven-development — TDD 红→绿→重构循环 |
步骤 1（强制） |
| Superpowers | systematic-debugging — 测试失败时诊断 |
异常处理时 |
| Superpowers | verification-before-completion — 完成前验证 |
完成前 |
GStack / OpenSpec / Spec-Kit / OMO 在本阶段不涉及。
前置门禁（Pre-flight）
0.1 上游确认
- task 阶段已过关（
engineTruth确认） - TASK.md 中无未解决的
[depends_on: ?] - 当前 git 分支干净（无未提交的临时修改）
0.2 Profile 判定
| Profile | 开发要求 |
|---|---|
full |
全 TDD（红→绿→重构）+ 全部 0.x 检查 + self-review(R1-R11) |
api/ui |
同 full |
lite |
TDD 可选，0.x 检查中的 0.5（破坏性变更）必须执行 |
micro/spike |
仅 0.1（grep 已有抽象）+ 0.5（破坏性变更） |
nano |
TDD 可选，0.5 必须执行 |
0.3 前置检查清单
- task 阶段已过关
- todo 列表已就绪（每个 T0X 一个 todo 项）
- 理解 TASK.md 的 verify 标准和 write_files 边界
步骤
dev 无 json 视图：过关证据为 .dev-complete（command + exitCode: 0）。实现边界仍来自 task.json / 渲染后的 TASK.md。
0. 上下文加载
先读 PHASE-CONTEXT.md 确认范围，再读 TASK.md 拿到任务清单。不写不在 TASK 中的功能。
0.1 沿用已有抽象 grep（强制）
写新代码前 grep 同类模式，贴入 SUMMARY：
# grep -rn "class.*Adapter" src/ → 找到 LLMAdapter 抽象基类
# grep -rn "from.*middleware" src/ → 找到 LoggingMiddleware 模式
不 grep 直接写 = 制造重复抽象。
0.2 扫 LESSONS（强制）
grep -rn "LESSON" .taiyi/changes/<slug>/ 2>/dev/null || echo "无 LESSONS"
对 active 条目声明差异。相同方案已记录失败教训 → 停手，选不同方案。
0.3 UI 任务额外检查
确认 UI-DESIGN.md 存在。颜色/字体/间距从 UI-DESIGN.md 派生。禁硬编码 hex。
0.4 Schema 变更检查
生成可逆迁移（up + down）。grep 确认数据库当前结构，避免迁移冲突。
0.5 破坏性变更高门槛
命中任一 → STOP，展示引用分析结果，等用户明确指示：
- 删除 ≥ 5 行代码
- 修改公共导出（export function / export class）
- 改 API 端点签名（path / method / request body）
- 改 DB Schema 列名或类型
1. TDD 红→绿→重构（强制）
<tdd_enforcement> STEP A — WRITE FAILING TEST ONLY
- Write the test that defines the expected behavior. Do NOT touch business logic yet.
- The test MUST be a real assertion (not console.log, not TODO).
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.
- 11d ago First seen · 259 lines · 21 tokens per session scan A ba8146ea6471
taiyi-dev is a skill published in the GitHub repository Dong90/oh-my-taiyiforge (888 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 3,188 once invoked, about $0.0001 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
kotlin-testing
Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
test-generation
Use when the user asks for tests, mentions TDD, or when new code has been written and needs test coverage.
spec-driven-development
Design and run a Spec-Driven Development (SDD) pipeline for AI software factories — where structured specifications are the input, AI agents generate the code, and quality gates enforce correctness at each phase: SPECIFY → DECOMPOSE → IMPLEMENT → VERIFY → DELIVER. Use when building or refining a spec-driven pipeline…
ag-referencia-tdd
TDD canonico Red-Green-Refactor — pipeline obrigatorio teste-primeiro. Reference skill carregada on-demand pelo modo --tdd da ag-1-construir.