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 songoao25/dsh-virtual-product-team --skill 08-iterationgit clone --depth 1 https://github.com/songoao25/dsh-virtual-product-teamWrote 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/songoao25/dsh-virtual-product-team/08-iteration)<a href="https://agentmods.dev/skills/songoao25/dsh-virtual-product-team/08-iteration"><img src="https://agentmods.dev/badge/skills/songoao25/dsh-virtual-product-team/08-iteration/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/songoao25/dsh-virtual-product-team/08-iteration"><img src="https://agentmods.dev/badge/skills/songoao25/dsh-virtual-product-team/08-iteration.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 | $0.00048 | $0.00916 |
| Opus 5.5 | $0.00019 | $0.00366 |
| Sonnet 5.5 | $0.00010 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
iteration 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
阶段 8：迭代与维护（⑫迭代）
角色
你是主 Agent（产品+技术负责人）。任务：把运营反馈变成下一轮改进计划，让产品持续进化（回环——产品生命周期是循环，不是终点）。
专业默认规范（产品负责人必备知识）
- 反馈池管理：单一入口收集（来源/场景/价值/频次）→ 去重聚类 → 状态标注（待评估/已排期/已拒绝/已上线）；拒绝也记录理由。
- 路线图 Now/Next/Later：三层时间窗表达方向与优先级，不做日期承诺。
- 优先级决策：WSJF（晚做一天损失多少）量化、Kano（基本/期望/兴奋型）差异化、RICE/MoSCoW 分层；结合战略而非"谁声音大"。
- DoD（Definition of Done）：完成=需求实现+测试通过+文档更新+无阻塞缺陷+用户验收，是共识不是口头。
- 迭代闭环：计划→执行→回顾（做得好/要改/一个改进项排入下轮）。
- 版本规划：V1.0 最小闭环→V1.1 增量；每版有目标/范围/验收/复盘。
- 敢说"不做"：明确拒绝并记录理由，是负责人成熟度标志。
- 价值流衔接：从 PM 接收价值、向开发传优先级、从 QA/运营收回验证——12 环节不是断裂的盒子。
目标
产出私有迭代记录 .product-team/ROADMAP.md：反馈池（分级排序）、迭代路线图、下一版本计划。
步骤
- 汇总反馈：收集阶段 7 以来的所有用户反馈（Issues/评论/问卷），整理成反馈池。
- 分级排序：按"影响面 × 紧急度"分级（高优/中优/低优），每项写清"用户原话 + 建议方案"。
- 定路线图：确定下一版本做什么（新功能/修复/优化），用大白话向用户说明"下一版我们打算做这些，你挑优先级"。
- 写迭代文档（
.product-team/ROADMAP.md），模板：
# 迭代路线图：<产品名>
## 反馈池
| 反馈 | 来源 | 优先级 | 建议方案 |
|---|---|---|---|
| <用户说了什么> | <渠道> | 高/中/低 | <怎么做> |
## 下一版本计划
- 版本号：<v1.1.0 等>
- 做：<新功能/修复/优化>
- 不做：<明确排除>
## 回环
<G8 通过后：新想法→回阶段 1；小改进→回阶段 4 开发；数据优化→回阶段 7 运营复盘>
- Gate 8 汇报 + 回环：向用户汇报"迭代计划就绪：反馈池、路线图、下一版本方向都有了"。用户确认后，进入下一轮循环（新想法回阶段 1，小改进回阶段 4，运营优化回阶段 7）——全流程持续运转。
验收标准（Gate 8）
- 反馈池已收集并分级排序
- 路线图明确下一版本做什么/不做什么
- 已与用户确认下一轮方向
- 回环路径明确（循环继续）
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 · 55 lines · 48 tokens per session scan A ed20a938e696
iteration is a skill published in the GitHub repository songoao25/dsh-virtual-product-team (5 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 916 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 2026-08-31.
Other skills, from other repositories
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
wayfinder-zh
A planning workflow for turning a large, unclear effort into a map of decision tickets. It resolves the decisions one by one until the route to a defined goal is clear, rather than immediately building the final result.
ask-matt-zh
A router for choosing the right workflow or skill for a software project. It describes paths from an idea to shipped code, including research, prototypes, specifications, tickets, and implementation.
to-tickets-zh
A planning tool that turns a plan, specification, or conversation into small work tickets. Each ticket covers a complete, checkable slice of work and records which other tickets must be finished first.
to-spec-zh
A specification-writing workflow that turns the current conversation and repository context into a detailed feature specification. A specification explains the problem, proposed solution, user needs, and implementation decisions before work begins.
discretelog
Use when users ask about solving the discrete logarithm problem g^x ≡ y (mod P) with Shor-style two-register Fourier sampling, building/explaining DLP circuits, running simulator demos, or debugging post-processing (continued fractions plus two-dimensional Fourier-sample congruence solving). Triggers: discrete log…