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 skills/weiyi88/cc-code/plan-prd-mvpnpx skills add weiyi88/cc-code --skill plan-prd-mvpgit clone --depth 1 https://github.com/weiyi88/cc-codeWrote 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/weiyi88/cc-code/plan-prd-mvp)<a href="https://agentmods.dev/skills/weiyi88/cc-code/plan-prd-mvp"><img src="https://agentmods.dev/badge/skills/weiyi88/cc-code/plan-prd-mvp.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 | $0.00107 | $0.01847 |
| Opus 5 | $0.00053 | $0.00924 |
| Sonnet 5 | $0.00021 | $0.00369 |
| Haiku 4.5 | $0.00011 | $0.00185 |
Grade A, and why
plan-prd-mvp 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cc-code:plan-prd-mvp — PRD 生成器(第一动作即 plan 模式)
⭐⭐⭐ 触发后第一动作 = call
EnterPlanMode工具。 所有探测 / 三件套 / 交谈都在 plan 模式内做,没有 plan 外窗口。 AI 从第一秒就在 plan only,Write/Edit 被锁死,无法逃避。
⛔ 三条铁律(违反即失败)
铁律 1:第一动作 call EnterPlanMode
触发后,在 call EnterPlanMode 之前,不许做任何动作:
- ❌ 不许先 Read Agent.md / status.md
- ❌ 不许先探测项目
- ❌ 不许先输出三件套
- ❌ 不许先输出"请主人审阅决策清单"
- ✅ 唯一允许的第一动作:call
EnterPlanMode工具
进入 plan 模式后,再做 Read / 探测 / 输出三件套 / 交谈(plan 模式允许 Read/Glob/Grep 和文字输出)。
铁律 2:禁批量决策清单
⛔ 禁止「全量输出决策清单,可全量接受 / 逐项修订 / 否决某项」。 必须逐点提问:一次只问一个模糊点,等主人答,再问下一个。
铁律 3:逐点循环至通顺
plan 模式内一直逐点提问,直到项目距 MVP 的所有逻辑 + 配置完全通顺,才 call ExitPlanMode。
一、流程
触发 /cc-code:plan-prd-mvp
↓
Step0 ⭐ call EnterPlanMode 工具(第一动作,不许先做别的)
↓ ──── 进入 plan 模式(只能 Read/Glob/Grep + 文字输出)────
Step1 Read Agent.md + status.md(同步角色与坐标)
Step2 探测项目(Read/Glob/Grep,守上下文最小化)
Step3 输出三件套(ascii 文字):
├─ 项目逻辑图(ascii:架构 + 业务生命周期 + 数据流)
├─ 前端原型图(ascii:关键页面 / 核心流程线框)
└─ MVP 差异点表格(ascii 框线:模块/现状/目标/gap/风险)
⚠️ 三件套是探测输出,辅助交谈,不是 ux.md
Step4 逐点循环提问(一次一个模糊点,不批量):
├─ 列出当前一个逻辑/配置模糊点
├─ 主人答疑 → 更新认知
└─ 检查:所有逻辑+配置通顺?
├─ 否 → 问下一个
└─ 是 → Step5
↓ ──── 通顺后 ────
Step5 call ExitPlanMode → 主人 approve
↓ ──── 退出 plan 模式 ────
Step6 Write .cc_code/active/prd.md(旧版归档 backup/YYYY-MM/)
Step7 提示走 /cc-code:agent-to-mvp
二、为什么第一动作就进 plan(最硬设计)
旧设计有「阶段一 plan 外探测 + 三件套」,AI 在 plan 外就有机会输出决策清单逃避 EnterPlanMode。 新设计第一动作就进 plan,AI 没有 plan 外窗口,从第一秒就在 plan only,Write/Edit 被锁死,无法逃避。
架构诚实:Claude Code 没有「系统级强制 AI call 某工具」的机制。把 EnterPlanMode 放第一动作 + 无 plan 外窗口,是软约束的极限 —— AI 要违反,得主动无视本文件第一行铁律。要再硬只能加 PreToolUse hook(检测 skill 激活时阻止未 plan 先 Write),但 hook 检测 skill 激活很复杂,且违背「一个东西只做自己的逻辑」。本方案是架构内最硬。
三、prd.md 产出结构(对齐模板)
1. 模块清单(# / 模块 / 优先级 P0P1P2 / 依赖 / 状态)
2. 逐模块:
├─ 职责(一句话,写不成 = 该拆)
├─ 核心规则 R1..Rn(每条可判真假,禁"优化/友好"等模糊词)
├─ 状态机(ascii,若有流转)
├─ 边界与异常
├─ 验收断言 A1..An(⭐编号永久稳定,whole-qa 的分母)
└─ 依赖
3. 全局规则 G1..Gn
4. 明确不做(Out of Scope)
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 · 138 lines · 107 tokens per session scan A ddf748929331
plan-prd-mvp is a skill published in the GitHub repository weiyi88/cc-code (5 stars, last pushed 8d ago), licensed MIT. It adds 107 tokens to every session and 1,847 once invoked, about $0.0005 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 skills, from other repositories
state-machine
Task lifecycle state transitions with validation gates. Defines states, triggers, and required proofs.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
mutation-testing
Mutation testing patterns for verifying test effectiveness. Use when analyzing branch code to find weak or missing tests.
planning
Planning work in small, known-good increments. Use when starting significant work or breaking down complex tasks.
testing
Testing patterns for behavior-driven tests. Use when writing tests or test factories.
davinci-define
Apply the 7 Da Vincian Principles to define problems, set direction, and reflect on life choices. Use for career decisions, goal setting, life planning, or when you need to clarify what the real question is before solving it.