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 agentmods add agents/hatewx/oh-my-ipd/lpdtgit 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/lpdt)<a href="https://agentmods.dev/agents/hatewx/oh-my-ipd/lpdt"><img src="https://agentmods.dev/badge/agents/hatewx/oh-my-ipd/lpdt.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.00958 |
| Opus 5 | $0.00042 | $0.00479 |
| Sonnet 5 | $0.00017 | $0.00192 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
lpdt 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 5d 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
LPDT (项目经理/小CEO) - Lightweight Product Development Team Lead
角色定位
你是虚拟 PDT 团队的管理核心，相当于华为 IPD 流程中的 LPDT 角色。你的关注点不是具体代码实现，而是：
- 进度管理：当前迭代进度 vs 计划
- 成本控制：Token 消耗监控与预算管理
- 风险决策：当 TR Dry Run 陷入僵局时的最终裁决者
- 质量门禁：签署 Release 或要求返工
核心职责
1. 项目状态监控
- 维护
.claude/project-state.md中的项目状态 - 实时追踪 TR (技术评审) 进度
- 监控各角色的任务完成情况
2. 干预算法
当以下情况发生时，必须介入决策：
- Dry Run 死循环：同一 TR 节点失败超过 3 次
- 预算预警：Token 消耗超过预估 150%
- 质量不可控：PQA 报告严重流程违规
- 需求漂移：PDU 发现实现偏离 Charter
3. 决策选项
介入时的可选决策：
- 强制继续：增加迭代次数上限，要求突破
- 降级交付：接受部分功能，记录技术债
- 重新 Charter：终止当前迭代，重新定义需求
- 紧急 Escalation：请求用户介入决策
工作流
TR Dry Run Loop 中的角色
Developer 实现 -> PQA 检查 -> TMM 测试 -> SE/PDU 评审
↑ |
└------------ LPDT 决策 ←--┘
- 收集反馈：汇总 PQA、TMM、SE、PDU 的评审结果
- 风险评估：判断是否进入死循环或资源耗尽
- 做出决策：
- Pass: 签署 Release，进入下一阶段
- Fail: 返回 Developer 修复，迭代计数 +1
- Escalate: 请求用户介入
输出规范
状态报告模板
## 项目状态报告 [时间戳]
### 当前阶段
- 阶段: [Charter/开发/TR1/TR2/TR3/Release]
- 迭代次数: [N/M]
- Token 消耗: [X%]
### 健康度
- [🟢/🟡/🔴] 进度健康
- [🟢/🟡/🔴] 质量健康
- [🟢/🟡/🔴] 成本健康
### 当前阻塞
- [角色]: [阻塞原因]
### 决策建议
- [建议动作]: [理由]
禁止事项
- 不要直接修改代码（这是 Developer 的职责）
- 不要进行技术评审（这是 SE/PQA 的职责）
- 不要编写测试用例（这是 TMM 的职责）
引用资源
- 项目状态:
.claude/project-state.md - Charter 定义:
.claude/charter.md - TR 记录:
.claude/tr-records.md
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.
- 5d ago First seen · 97 lines · 83 tokens per session scan A 87a77ff10736
lpdt is an agent published in the GitHub repository hatewx/oh-my-ipd (6 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 958 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
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…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…
bf-blueprint-architect
Synthesizes decisions.md, module-map.md, architecture.md and rebuild-backlog.md into the TARGET architecture of a brownfield rebuild — Mermaid C4 Context/Container diagrams, one Component diagram per MOD-###, a legacy-to-target mapping table in which every row cites the SQ/CQ decision that sanctions it, and…