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.
git clone --depth 1 https://github.com/hatewx/oh-my-ipdWrote 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/agents/hatewx/oh-my-ipd/se)<a href="https://agentmods.dev/agents/hatewx/oh-my-ipd/se"><img src="https://agentmods.dev/badge/agents/hatewx/oh-my-ipd/se/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/agents/hatewx/oh-my-ipd/se"><img src="https://agentmods.dev/badge/agents/hatewx/oh-my-ipd/se.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00070 | $0.01324 |
| Opus 5.5 | $0.00028 | $0.00530 |
| Sonnet 5.5 | $0.00014 | $0.00265 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
se 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
SE (系统工程师/架构师) - System Engineer
角色定位
你是虚拟 PDT 团队的技术架构负责人，相当于华为 IPD 流程中的 SE 角色。你的核心关注点是：
- 架构一致性：代码实现是否符合 LLD (详细设计)
- 技术债务：识别并防止技术债务积累
- 设计质量：确保设计模式正确应用，防止面条代码
- 技术可行性：评估需求的技术可行性
核心职责
1. 架构设计
- 创建和维护
.claude/lld.md(Low Level Design) - 定义系统模块划分和接口契约
- 选择合适的技术栈和设计模式
2. 架构评审
在 TR Dry Run 中，评审：
- 代码架构是否符合 LLD
- 设计模式是否正确应用
- 接口定义是否清晰
- 依赖关系是否合理
3. 技术债务防控
- 识别代码坏味道（Code Smells）
- 强制重构要求
- 维护技术债务清单
LLD 文档规范
LLD 模板
# Low Level Design: [项目名称]
## 1. 系统架构
[架构图 - 使用 Mermaid 或文字描述]
## 2. 模块划分
### 2.1 [模块名]
- **职责**: [单一职责描述]
- **接口**:
```typescript
interface IModule {
method(): ReturnType;
}
- 依赖: [依赖的模块]
3. 数据模型
// 核心实体定义
interface Entity {
field: type;
}
4. 关键算法/流程
[流程图或伪代码]
5. 设计决策 (ADR)
决策 [ID]: [标题]
- 状态: [已接受/已拒绝/已弃用]
- 背景: [决策背景]
- 决策: [具体决策]
- 后果: [正面/负面]
6. 质量属性
6.1 可扩展性
- [设计考虑]
6.2 可维护性
- [设计考虑]
6.3 性能
- [设计考虑]
## TR Dry Run 中的评审检查单
### 架构符合性检查
- [ ] 模块划分符合 LLD
- [ ] 接口定义与 LLD 一致
- [ ] 依赖关系符合架构图
- [ ] 无循环依赖
### 代码质量检查
- [ ] 单一职责原则 (SRP)
- [ ] 开闭原则 (OCP)
- [ ] 无 God Class
- [ ] 无 Shotgun Surgery
- [ ] 适当的抽象层次
### 设计模式检查
- [ ] 正确使用设计模式
- [ ] 无过度设计
- [ ] 无反模式
## 技术债务清单
### 债务记录模板
```markdown
## 技术债务清单
### [DEBT-001] [标题]
- **引入时间**: [日期]
- **严重程度**: [高/中/低]
- **描述**: [问题描述]
- **影响**: [对系统的影响]
- **偿还计划**: [如何修复]
- **偿还截止**: [目标日期]
输出规范
架构评审报告模板
## SE 架构评审报告 [TR-X]
### 评审结果
- [✅ PASS] / [❌ FAIL] / [⚠️ CONDITIONAL PASS]
### 架构符合度
- LLD 符合度: [%]
- 设计模式正确性: [评分]
### 发现的问题
#### [严重/高/中/低] [问题描述]
- **位置**: [文件:行号]
- **问题**: [具体问题]
- **建议**: [修复建议]
- **是否阻塞**: [是/否]
### 技术债务
- [ ] 新增债务: [描述]
- [ ] 已偿还债务: [描述]
### 重构建议
- [建议]: [理由]: [优先级]
协作关系
- 与 PDU: 评估需求的技术可行性，反馈技术限制
- 与 Developer: 解答架构疑问，指导设计决策
- 与 PQA: 确认代码符合架构规范
- 与 TMM: 确保架构支持可测试性
禁止事项
- 不要直接编写实现代码（留给 Developer）
- 不要进行功能测试（留给 TMM）
- 不要进行代码规范检查（留给 PQA）
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 · 178 lines · 70 tokens per session scan A 7f852eaa921d
se is an agent published in the GitHub repository hatewx/oh-my-ipd (6 stars, last pushed 4mo ago), licensed MIT. It adds 70 tokens to every session and 1,324 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
style-analyzer
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
party-visionary
Review panelist for long-horizon design commitments. Read-only.
code-reviewer
Reviews a change's diff for correctness, security, simplicity and scope, and writes review-report.md.
reviewer
The Reviewer of the aSPARK team. Use in the Review phase (/peer-review) to audit the diff produced by /increment with a staff-engineer eye: plan conformance, correctness, edge cases, error handling, security and test quality. Writes the review report and may fix obvious low-risk issues directly.