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-reviewgit 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-review)<a href="https://agentmods.dev/skills/dong90/oh-my-taiyiforge/taiyi-review"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-review/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-review"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 180 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]
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 | $0.00026 | $0.02807 |
| Opus 5.5 | $0.00010 | $0.01123 |
| Sonnet 5.5 | $0.00005 | $0.00561 |
| Haiku 4.5 | $0.00003 | $0.00281 |
Grade A, and why
taiyi-review 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
taiyi-review — 合并前评审
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（status → continue --approver；legacy：npx taiyi complete） |
全程 |
| GStack | review — 使用 GStack review 做 diff 安全分析 |
Round 1 FR 步骤前（可选） |
| OMO | 作为 review 门控的工作流入口 | 全程 |
Superpowers / OpenSpec / Spec-Kit 在本阶段不涉及。
前置门禁（Pre-flight）
0.1 上游确认
- test 阶段已过关（TEST.md 存在，测试全部通过）
- README.md、CLAUDE.md 等文档的 Diff 已确认
- 当前 git 分支对比 base 的完整 Diff 可读
0.2 Profile 判定
| Profile | REVIEW.md 要求 |
|---|---|
full |
4 rounds 完整评审（diff/架构/测试/文档）+ 修订循环 + ⭐ 总体评分 |
api/ui |
同 full |
lite |
简化为 3 rounds（跳过架构评审）+ 修订循环 + ⭐ 评分 |
spike/micro |
简化到 1 round（代码可读性）+ ⭐ 评分 |
nano |
跳过 |
0.3 前置检查清单
- TEST.md 存在且测试全部通过
- git diff 与 base 分支的差异已清楚（
git diff base-branch..HEAD --stat） - 无未提交的改动
步骤
工件契约
| 层 | 路径 | 职责 |
|---|---|---|
| 语义真源 | review.json |
Zod（src/schemas/review.ts） |
| 生成视图 | REVIEW.md |
hbs（src/templates/review.hbs） |
| 流程 | 本 Skill | 4 rounds、修订循环、⭐ 评分 |
工作流：review-loop 机器审查 → 更新 json findings → render <slug> review → status → continue --approver "名"。
详见 docs/taiyi/artifact-contract.md。
json 字段（Zod 摘要）
| 字段 | 要求 |
|---|---|
title |
评审标题 |
findings |
severity / description / file / line / resolved |
code_quality |
可选；⭐ 各维度 1–5 |
test_coverage |
可选；层覆盖摘要 |
blocking_items / suggestion_items |
可选 |
verdict / summary |
可选；合并门槛与总结 |
除更新 Finding 状态外，不要手改 reviewer 生成的 REVIEW.md 结构；结构化数据以 review.json 为准。
写作指引（填入 json，render 生成 REVIEW.md）
除了修改实现外，不要修改 reviewer agent 生成的 REVIEW.md 内容。
1. Round 1 — 功能性 FR（Diff 角度）
审查 git diff 中的每个改动（逐文件），检查：
- 逻辑正确性（边界、竞态、类型安全）
- 与 AC 的一致性（每段代码能不能追踪到某条 AC？）
- 错误处理完整（每条错误路径有 check / catch）
- Scope 管控（改动是否超出 TASK.md write_files？）
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 · 233 lines · 26 tokens per session scan A 7bf63e8c0ef8
taiyi-review is a skill published in the GitHub repository Dong90/oh-my-taiyiforge (859 stars, last pushed 17d ago), licensed MIT. It adds 26 tokens to every session and 2,807 once invoked, about $0.0001 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
pn-best-of-n
Run 2–3 competing implementations of the same spec in isolated worktrees, eliminate failures via objective gates, then judge survivors with a separate premium-tier pass. Use for ambiguous algorithm/API/refactor choices with strong tests — not auth/security paths.
pn-skeptic-challenge
Question the proposed approach and verify it is the best possible way. List alternatives and tradeoffs; suggest plan changes if a simpler or better path exists. Gate on confirmation before proceeding.
pn-deprecation-and-removal
Sunsetting APIs, features, and dead code — deprecation levels, migration windows, Hyrum's Law, zombie code removal. Use when removing or replacing user-visible behavior, public APIs, or long-lived flags; not the same as framework version upgrades alone.
pn-deslop
Remove AI-generated code slop and clean up code style. Use in review passes and before shipping; part of the pn-review-optimize-loop.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.