agentmods.dev

product-discovery

product-discovery is a skill for Claude Code from infra403/agentic-engineering-lab. It costs 141 tokens per session (1,590 once invoked), scanned A, original, MIT.

A structured workflow for designing software architecture and technical specifications. It uses decision frameworks to choose architecture styles, data systems, security patterns, and related technical approaches.

In plain words
What is it for?
Use it to design system architecture, choose databases or messaging patterns, define technical specifications, and review security-related decisions.
Why use it?
It helps make architecture decisions traceable and consistent instead of relying only on intuition.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions subagents.

Part of the product-design plugin — 3 skills, 4 commands, 10 agents shipped together

not rated 5repo 4mo ago A scan 141 tokens original MIT

Good fit Use it to design system architecture, choose databases or messaging patterns, define technical specifications, and review security-related decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/infra403/agentic-engineering-lab/product-discovery
View source ↗ infra403/agentic-engineering-lab
Install

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.

Any agent
npx skills add infra403/agentic-engineering-lab --skill product-discovery
Clone the repo
git clone --depth 1 https://github.com/infra403/agentic-engineering-lab

Made for: Claude Code.

Or install product-design, the plugin that ships this one along with the rest of its 3 skills, 4 commands, 10 agents.

Wrote 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.

agentmods badge for product-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/infra403/agentic-engineering-lab/product-discovery.svg)](https://agentmods.dev/skills/infra403/agentic-engineering-lab/product-discovery)
Your own site
<a href="https://agentmods.dev/skills/infra403/agentic-engineering-lab/product-discovery"><img src="https://agentmods.dev/badge/skills/infra403/agentic-engineering-lab/product-discovery.svg" alt="Measured on agentmods" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,590 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00141 $0.01590
Opus 5 $0.00071 $0.00795
Sonnet 5 $0.00028 $0.00318
Haiku 4.5 $0.00014 $0.00159

Measured 7d ago against content hash 98322ef5483b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

product-discovery 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.

claude-code/plugins/product-design-plugin/skills/product-discovery/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Discovery — 产品需求发现与分析

核心理念

知识先行，角色后置。
每个需求决策必须引用 knowledge/ 中的决策框架 [K]，不凭直觉。
生成（Generator）和评估（Evaluator）由不同角色执行。

文件结构

.claude/skills/product-discovery/
├── SKILL.md                              ← 你在这里
├── knowledge/requirements-quality.md     ← SAiP+Clean Arch: QAS/ATAM/分层
├── knowledge/theory-of-constraints.md    ← TOC: 五聚焦步骤/瓶颈/吞吐量会计
├── roles/product-analyst.md              ← Generator: 需求发现 + 优先级
├── roles/reviewer.md                     ← Evaluator: 对抗性评估
├── references/PROTOCOL.md                ← 反 LLM 缺陷协议（全程约束）
└── templates/
    ├── checkpoint.md                     ← 阶段检查点格式
    ├── progress.md                       ← design-progress.json 格式
    └── requirements.md                   ← 需求规格输出格式

启动步骤

  1. 读取本文件 — 了解工作流
  2. 读取 .claude/skills/product-discovery/references/PROTOCOL.md — 了解反 LLM 缺陷约束
  3. 创建 design-progress.json — 格式见 .claude/skills/product-discovery/templates/progress.md
  4. 加载 .claude/skills/product-discovery/knowledge/requirements-quality.md — 需求分析的核心知识
  5. 加载 .claude/skills/product-discovery/knowledge/theory-of-constraints.md — TOC 约束理论
  6. 走收敛循环 — GENERATE → EVALUATE → RESOLVE → CHECK
  7. 产出 checkpoint — checkpoint-1-discovery.yaml

Sprint 契约

  • 输入： 用户的产品描述
  • 产出： 结构化需求列表（FR-xxx / NFR-xxx）+ checkpoint-1-discovery.yaml
  • 收敛标准： Rubric 每项 ≥ 7/10
  • 迭代： 持续直到收敛（不限轮次）
  • Generator： .claude/skills/product-discovery/roles/product-analyst.md
  • Evaluator： .claude/skills/product-discovery/roles/reviewer.md（或独立 Subagent）

收敛循环

┌─────────────────────────────────────────────────┐
│  GENERATE  →  EVALUATE  →  RESOLVE  →  CHECK    │
│  (生成方案)    (独立评估)    (修正)      (收敛检查) │
│      ▲                                  │       │
│      │            未收敛                 │       │
│      └──────────────────────────────────┘       │
│               已收敛 ↓                           │
│          CHECKPOINT（固化 + 交接）                │
└─────────────────────────────────────────────────┘

Read the full file on GitHub · 121 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 7d ago First seen · 121 lines · 141 tokens per session scan A 98322ef5483b

Subscribe to this mod's changes

product-discovery is a skill published in the GitHub repository infra403/agentic-engineering-lab (5 stars, last pushed 4mo ago), licensed MIT. It adds 141 tokens to every session and 1,590 once invoked, about $0.0007 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.

Planning
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens