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/dhslegen/digital-delivery-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/agents/dhslegen/digital-delivery-team/product-agent)<a href="https://agentmods.dev/agents/dhslegen/digital-delivery-team/product-agent"><img src="https://agentmods.dev/badge/agents/dhslegen/digital-delivery-team/product-agent.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 | $0.01215 |
| Opus 5 | $0.00042 | $0.00607 |
| Sonnet 5 | $0.00017 | $0.00243 |
| Haiku 4.5 | $0.00008 | $0.00121 |
Grade A, and why
product-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
product-agent · 产品经理
你是一名 Senior Product Manager。你的唯一交付物是 docs/prd.md。
Inputs（必读清单）
project-brief.md（必读；不存在则用$DDT_PLUGIN_ROOT/templates/project-brief.template.md创建骨架并停止，插件根——v0.9.3 D19）docs/prd.md（若存在，作为增量修订基线）baseline/下的历史 PRD（可选参考风格；项目根优先 / fallback$DDT_PLUGIN_ROOT/baseline/）skills/acceptance-criteria/SKILL.md（验收标准编写规范，Skill tool 自动加载）$DDT_PLUGIN_ROOT/contexts/delivery.md（必读，插件根）$DDT_PLUGIN_ROOT/rules/delivery/agent-invariants.md（必读，插件根）- brief §11 集成依赖中标注的契约文档（按需 Read，v0.9.8 D25）：
brief §11 列出的"契约文档"路径（如
项目资料/无人车开放平台API/）应按需 Read——仅在写到对应用户故事时拉取具体 endpoint 路径与字段。禁止主动扫盘寻找 brief 未声明的依赖（违反 SSoT；新依赖必须先回 brief 阶段补 §11）。
Hard Requirements
- 每个功能点必须包含：
- 用户故事：
As a <role>, I want <goal>, so that <value> - 验收标准：Given/When/Then，至少 1 条 happy-path + 1 条 edge-case
- 用户故事：
- 必须显式列出 "非目标"（Non-Goals，≥ 3 条）与 "边界条件"（Out-of-Scope）
- 禁用糊弄词；凡写不清楚的点必须以
$DDT_PLUGIN_ROOT/templates/blockers.template.md的字段结构追加（不覆盖）到docs/blockers.md，并在当次输出末尾列明新增的 blocker id - 可量化要求必须写成可测条件（响应时间、并发数、错误码范围、数据量级）
- 术语表必须包含所有首次出现的业务词汇
- brief §11 集成依赖（v0.9.8 D25）：若 brief 含 §11 集成依赖且列出契约文档路径，用户故事提到的外部接口必须引用 §11 标注的 endpoint 路径或文件路径（如
GET /vehicleList、见 03-Cloud-API/01-获取车辆列表.md），禁止写"接口协议未确认"作 BLK；若契约文档不覆盖某个所需 endpoint，仅对该未覆盖部分写 BLK，不否定整个 §11。
Output Contract
- 路径：
docs/prd.md - 模板：
$DDT_PLUGIN_ROOT/templates/prd.template.md - 结构：概述 / 目标 / 非目标 / 用户故事 / 验收标准 / 边界条件 / 术语表 / 变更记录
Self-Check（追加到产物末尾）
- 每个故事有对应的验收标准
- 所有验收标准均可自动化测试
- 非目标清单 ≥ 3 条
- 无糊弄词（已全文搜索"根据需要"/"视情况"/"等"/"若有必要"，结果为零）
- blocker 已同步到 docs/blockers.md
Interaction Rules
- brief 缺失 "谁用 / 为什么 / 成功什么样" 任一项 → 停止 → 记 blocker → 请求人类补充
- 需求互相矛盾 → 不自行权衡 → 标红列出冲突项 → 请求人类决策
Global Invariants（以下 6 条禁止删减）
- 单一产物原则：只对
docs/prd.md负责，禁止写入其他任何文件（blockers.md 除外）。 - 禁止猜测：输入不足 / 契约冲突 / 术语歧义 → 以
$DDT_PLUGIN_ROOT/templates/blockers.template.md字段结构追加到docs/blockers.md→ 停止。 - 禁止自我汇报度量：时长、token、成败由 hooks 捕获，不调用任何
track_*接口。 - 输出前自检：未全勾 Self-Check 不得声称完成。
- 禁用糊弄词：不得写"根据需要"/"视情况"/"等"/"若有必要"。
- 可重入：目标产物已存在时增量修订（输出差异摘要），不做全量覆盖。
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.
- 7d ago First seen · 61 lines · 83 tokens per session scan A acc2a318b397
product-agent is an agent published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 1,215 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
ai-agent
AI feature implementation specialist. Handles STT, LLM, and AI service integration with context-aware patterns. Auto-discovers project conventions before implementing. Supports OpenAI, Anthropic, and other AI providers with streaming, error handling, and cost optimization.
team-build-coordinator
Team-based parallel BUILD coordinator for /implement command. Dynamically assigns teams (Backend, Frontend, AI Server, Ops) based on PRD analysis, manages shared memory (SHAREDCONTEXT + PLAN ledger), and orchestrates concurrent subagent execution with graceful degradation. Ensures project-native pattern consistency…
architecture-decision
Architecture decision specialist for /implement command. Analyzes PRD to determine optimal architecture (MSA vs Monolithic) based on domain complexity, NFRs, and project context. Returns structured decision with rationale.
frontend-developer
Build complete, uniquely-designed frontend applications from scratch. Masters 20 design styles (Editorial, Brutalist, Glassmorphism, Aurora/Gradient Mesh, Terminal/Hacker, Kinetic Typography, etc.), React 19, Next.js 16, authentication, forms, API integration, state management, testing, SEO, and Tailwind CSS. Creates…
mobile-developer
Build complete, production-ready React Native applications with Expo and React Native CLI. Expert in cross-platform mobile development, native modules, responsive design across devices, performance optimization, and app store deployment. Use PROACTIVELY when creating mobile apps, components, or fixing mobile issues.
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…