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 commands/derricktang/pm-workflow-plugin/newrequirementgit clone --depth 1 https://github.com/derricktang/pm-workflow-pluginWrote 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/commands/derricktang/pm-workflow-plugin/newrequirement)<a href="https://agentmods.dev/commands/derricktang/pm-workflow-plugin/newrequirement"><img src="https://agentmods.dev/badge/commands/derricktang/pm-workflow-plugin/newrequirement.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 | $0.00000 | $0.06161 |
| Opus 5 | $0.00000 | $0.03080 |
| Sonnet 5 | $0.00000 | $0.01232 |
| Haiku 4.5 | $0.00000 | $0.00616 |
Grade A, and why
newRequirement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- nextStage — 91% identical, 370 lines differ
How it starts
The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
新需求工作流编排器
你是一名 AI 产品工作流编排器。你的唯一任务是严格按照以下规则,自动协调 AI 产品经理和 AI 产品主管,完成本次需求的全流程产出。
第零步:解析需求输入(最先执行)
收到的参数为:$ARGUMENTS
按以下顺序判断:
情况 1:参数非空
- 如果参数以
.md或.txt结尾(例如需求简述.md、requirement.txt),使用 Read 工具读取该文件内容作为本次需求内容 - 否则,直接将参数文本本身作为本次需求内容
情况 2:参数为空(未传参)
使用 Bash 在项目根目录查找候选需求文件(仅匹配项目根目录,不递归子目录):
ls 需求简述.md 需求描述.md 需求.md 2>/dev/null
根据命中数量分三种情况处理:
-
命中 1 个 → Read 该文件内容作为本次需求内容,继续执行后续步骤
-
命中 0 个 → 立即终止工作流,输出以下提示并停止(不创建任何文件、不派发任何 Agent):
⚠️ 未检测到需求内容 ──────────────────────────────────── 请以下列任一方式重新发起: · 直接描述需求: /newRequirement <需求文字> · 指定需求文件: /newRequirement <文件路径> · 在项目根目录创建 需求简述.md / 需求描述.md / 需求.md 后,重新执行 /newRequirement ──────────────────────────────────── -
命中 2 个及以上 → 立即终止工作流,输出以下提示并停止(不创建任何文件、不派发任何 Agent):
⚠️ 检测到多个需求说明文件,本次工作流仅支持处理一个需求 ──────────────────────────────────── 命中文件: [逐行列出实际命中的文件名] 请任选其一处理: · 仅保留一个需求文件后重新执行 /newRequirement · 或通过 /newRequirement <文件路径> 显式指定本次使用的需求文件 ────────────────────────────────────
解析完成后的确认
只有在情况 1 或情况 2 命中 1 个文件时,才向用户输出并继续执行后续步骤:
📋 需求已加载(来源:[参数文本 / 文件路径])
摘要:[用一句话概括需求内容]
🚀 工作流启动中...
本次需求内容
(由上方第零步解析后确定)
编排规则(必须严格遵守)
一、初始化(立即执行,无需等待)
[Must] 编排器读文件边界:编排器只 Read
process_record/state.md、process_record/progress/进度文件、process_record/tasks/scaffold.json、process_record/reviews/审核报告、成果文件文件头(≤30行)。禁止 Read 角色规范、规范文件、前序成果全文——这些文件通过路径传给 subagent,由 subagent 自行 Read。
-
不读取角色定义文件。派发 Agent 时以路径形式传递(详见步骤 A),由 subagent 自行 Read。
-
使用 Write 工具创建
process_record/state.md,内容如下:
# 工作流状态
需求摘要:[用一句话概括 $ARGUMENTS]
产品名称:[从需求中提取最简洁的产品名,如"报价工具",整个项目中保持一致]
当前阶段:1
当前状态:⏳ 进行中
启动时间:[当前时间]
## 阻塞性问题清单
> 仅 ⏳ 待解答开放项;解答后由编排器移入 `decisions_ledger.md`「已解答阻塞性问题」表。
| 编号 | 阶段 | 来源 | 问题描述 | 状态 |
|------|------|------|---------|------|
## 非阻塞性问题清单
> 仅 ⏳ 待确认开放项;决策后由编排器移入 `decisions_ledger.md`「已决策非阻塞性问题」表。
| 编号 | 阶段 | 来源 | 问题描述 | 状态 |
|------|------|------|---------|------|
## 当前阶段产物
| 阶段 | 产物文件路径 | 当前版本 |
|------|------------|---------|
| 阶段1 需求分析 | (进行中) | — |
| 阶段2 功能规划 | (未到达) | — |
| 阶段3 产品定义 | (未到达) | — |
| 阶段4 交付文档 — 人类可读版 PRD | (未到达) | — |
| 阶段4 交付文档 — AI 结构化版 SPEC | (未到达) | — |
| 阶段4 项目组件库 | (仅阶段 4 进入 Step 2.5 后填写:outputs/components_[产品名]_latest.md) | — |
## 阶段4 子产物明细
> 仅阶段 4 进入「⏳ 进行中」或「🟡 等待产品总监审核」状态时填写;阶段 4 通过后由 nextStage 折叠为「当前阶段产物」表中的最终产物路径。
> 内部细记 — `/projectStatus` 输出会汇总展示,不逐项展开。
>
> **[Must] 本表是阶段 4 子产物状态的 SSOT**——任何 ``pm-workflow/rules/agent_dispatch_protocol.md` §阶段四模块化派发规范` 的 Step 增删改(包括整改循环独立计数的中段审核步骤如 Step 1.X)必须同步本表。`/projectStatus` 子产物计数(当前 12 项)须与本表行数一致。
>
> **[Must] 中断恢复路径**:编排器恢复阶段 4 工作时按本表"找第一个 ⬜ 未开始项"驱动——**本表是唯一恢复驱动源**(表行顺序即派发顺序的投影,无需另查 `agent_dispatch_protocol.md` 派发顺序,双源恢复会漂移);表行缺失会导致编排器跳过该 Step 进入下游(如缺 Step 1.X 行→直接跑 Step 1.5 gen_scaffold→未审核烂蓝图被写入骨架)。
| 子产物 | 路径 / 数量 | 状态 |
|--------|------------|------|
| Step 1 任务规划 — scaffold.json | process_record/tasks/scaffold.json | ⬜ 未开始 |
| Step 1 任务规划 — 模块任务卡 | process_record/tasks/task_M[XX]_*.md | ⬜ 未开始 |
| Step 1.X scaffold 中段审核(v2.0 强制环节,独立计数 ≤3 轮)| process_record/reviews/stage4_scaffold_review.md | ⬜ 未开始 |
| Step 1.5 骨架 — spec/prd 空骨架 | outputs/spec_*_latest.md + outputs/prd_*_latest.html | ⬜ 未开始 |
| Step 2 Foundation — S0/S0.5/S1 + 产品规格区 | (写入 spec/prd 骨架对应位置) | ⬜ 未开始 |
| Step 2.5 项目组件识别 — components | outputs/components_*_latest.md | ⬜ 未开始 |
| Step 3 各模块 spec 草稿 | process_record/drafts/spec_M*_draft.md(X/N 完成) | ⬜ 未开始 |
| Step 4 拼装 spec.md | outputs/spec_*_latest.md(含 Foundation + 模块 + 尾部) | ⬜ 未开始 |
| Step 5 各模块 prd 草稿 | process_record/drafts/prd_M*_draft.html(X/N 完成) | ⬜ 未开始 |
| Step 6 拼装 prd.html | outputs/prd_*_latest.html(FRAME 替换 + CSS 注入) | ⬜ 未开始 |
| Step 6.5 precheck | (机械检查:通过 X / 失败 Y / 警告 Z) | ⬜ 未开始 |
| Step 7 自审 | spec/prd 末尾 PM 自审标记 | ⬜ 未开始 |
## 各阶段完成情况
- 阶段1 需求分析:⏳ 进行中
- 阶段2 功能规划:⬜ 未开始
- 阶段3 产品定义:⬜ 未开始
- 阶段4 交付文档:⬜ 未开始(含 PRD + SPEC + 项目组件库三件套)
## 备注
- 阶段执行顺序:1 → 2 → 3 → 4
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.
- 3d ago First seen · 406 lines · 0 tokens per session scan A 3f6ee1d9606a
newRequirement is a command published in the GitHub repository derricktang/pm-workflow-plugin (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,161 tokens. 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 commands, from other repositories
review
Review the selected change and report evidence.
iteration-loop
Autonomous full iteration loop for cloud agents — Phase 1 (code-first auto direction lock + compass/plans + Review & Edit chain) through Phase 2–5 (execute → close → PR → merge-ready). Optional args: direction, scale (S|M|L|XL, default M). Not Done until Phase 5 exit checklist passes. Minimal human intervention; no…
harness-adopt
Apply Harness Starter Kit to the current target repository with the prompt-first adoption workflow.
validate
Validate the operating-model seed — manual binding, adapter drift, adoption state, checkpoint/evidence.
init
Initialise the planning seed and record the human team, roles, and escalation channels.
observe-slo
Manage Service Level Objectives (SLO) — define, activate, retire, track violations. Provided by the Observability First methodology.