agent-mvp

agent-mvp is a skill for Claude Code, Codex from weiyi88/cc-code. It costs 27 tokens per session (2,688 once invoked), scanned A, original, MIT.

An execution workflow for building a minimum viable product, meaning the smallest complete version of a product that can be tested with users. It reads approved plans, assigns development and testing in order, and coordinates fixes until the planned checks pass.

In plain words
What is it for?
Use it to implement a planned product from its requirements, interface, project, data, and API documents, then run staged development, testing, and final full-project checks.
Why use it?
It keeps implementation from drifting into unapproved requirements and prevents development from skipping testing. It also provides a structured path from finished plans to a tested product.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also agents/openai.yaml present.

Part of the cc-code plugin — 17 skills, 3 agents, 1 hook shipped together

Good fit Use it to implement a planned product from its requirements, interface, project, data, and API documents, then run staged development, testing, and final full-project checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/weiyi88/cc-code/agent-mvp
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 weiyi88/cc-code --skill agent-mvp
Clone the repo
git clone --depth 1 https://github.com/weiyi88/cc-code

Made for: Claude Code, Codex.

Or install cc-code, the plugin that ships this one along with the rest of its 17 skills, 3 agents, 1 hook.

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 agent-mvp

README.md
[![agentmods](https://agentmods.dev/badge/skills/weiyi88/cc-code/agent-mvp/github.svg)](https://agentmods.dev/skills/weiyi88/cc-code/agent-mvp)
Your own site
<a href="https://agentmods.dev/skills/weiyi88/cc-code/agent-mvp"><img src="https://agentmods.dev/badge/skills/weiyi88/cc-code/agent-mvp/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.

agentmods 80×15 button for agent-mvp

Your own site · 80×15
<a href="https://agentmods.dev/skills/weiyi88/cc-code/agent-mvp"><img src="https://agentmods.dev/badge/skills/weiyi88/cc-code/agent-mvp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,688 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 $0.00027 $0.02688
Opus 5.5 $0.00011 $0.01075
Sonnet 5.5 $0.00005 $0.00538
Haiku 4.5 $0.00003 $0.00269

Measured today against content hash 25fdb2a57c4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-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 today.

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.

skills/agent-mvp/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-mvp — 双 agent × cc-code 驱动 MVP 执行编排器

纯执行器:需求与契约只读不产——一切规划产物(prd / ux / project / data / api)由 /cc-code:plan-mvp 商讨定稿。本命令读定稿文档直接开发,中途零确认,只在 FAIL 3 轮升级时交人。 校准铁律:每一个阶段完成后,必须先执行 /cc-code:cc-code 校准当前状态(重读 Agent.md/status.md,重锁角色与坐标),确认无误后再进入下一阶段。未校准禁止推进。校准是机器自检,静默进行,不以「请确认」的姿态打扰人。 串行铁律:严守 Dev → QA 顺序,由 .cc_code/active/Agent.md 锁定当前角色,禁止跨角色思考与跳序。

与规划命令的分工(两两配对,单一职责)

 plan-mvp(人参与)              agent-mvp(本命令,纯机器)
 商讨 → 逐点循环至通顺               读定稿文档
 落盘 prd/ux/project/data/api  ──►  Dev 编码 → QA 验收(≤3 轮回环)
 对话内确认,落盘即定稿               阶段全 PASS → agent-whole-qa 收口

前置检查(启动时一次性)

  1. 确认项目根存在 .cc_code/(否则提示先 /cc-code:init)。
  2. 定稿体检:active/prd.md 有 §1.5 验收断言主表,且 ux.md / project.md / data.md / api.md 齐备。缺任一 → ⛔ 拒跑,报「规划产物未定稿,请先走 /cc-code:plan-mvp」,绝不现场补需求。
  3. 确认双 agent 可用:dev / qa。
  4. 确认测试基建:读 project.md §六「测试基建契约」取测试根 / glob / 运行命令。缺失或未填实则把「补齐测试基建 + 回填 project.md §六」作为 Dev 阶段首个任务。 同理读 project.md §七「日志契约」:选库 / 配置值未填实,或门面与 requestId 入口未落地 → 把「搭日志基建 + 回填 §七」并入 Dev 首个任务。
  5. 索引体检(静默):codegraph status --json 读三字段 —— initialized:false → 报一行(⛔ 不自动重建);pendingChanges 非 0 → 静默 codegraph sync;reindexRecommended:true → 报一行建议。CLI 未装则静默跳过,全流程照跑(精准回归降级为全量)。⛔ 健康时一个字都不提。
  6. 执行 /cc-code:cc-code 完成会话开启协议,锁定当前阶段与角色。
  7. 阶段来源:读 project.md 的阶段拆分章节。有 → 按阶段逐段推进;无 → 整体作单阶段跑完(⛔ 不自行拆阶段,拆分是规划的职责)。

生命周期总览

启动校准 → ①Dev → 校准 → ②QA → 校准
                              │
                    ┌─────────┴──────────┐
                    ▼                    ▼
              FAIL→回Dev(≤3)         PASS→阶段结算→校准
                    │                    ▼
            3轮仍FAIL→升级(交人)     还有阶段? →回①
                                         ▼
                                 全PASS → MVP收口

阶段执行规范

每阶段严格按「读 / 做 / 跑 / 输出 / 写」执行,完成即校准。

① Dev 段(agent: dev)

项 内容
读 status, prd, ux, project(含阶段拆分章节), data, api
做 按规格实现 src + 三层测试;遵循 project.md 约定
跑 Agent(dev) → 内部 Read/Edit/Write;自检:pnpm lint → tsc --noEmit → pnpm test → pnpm test:e2e
输出 业务代码 + 测试(落 project.md §六 声明的测试根)+ 完成报告(文件清单 + pass/fail)
写 src/, project.md §六 声明的测试根
⭐ 完成后 算精准回归面:codegraph affected <本段改动的源文件...> → 得测试文件清单,传给 ②QA 段。非 .spec/.test 命名的测试补跑 --filter "<project.md §六 登记的 glob>"。合并去重后即「本段回归范围」
✅ 完成后 执行 /cc-code:cc-code 校准

Read the full file on GitHub · 126 lines

Files

What ships with it

1 file 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. today Changed · +1 lines 25fdb2a57c4a
  2. 1mo ago Changed · -90 tokens per session 0ccb37d5e743
  3. 1mo ago First seen · 125 lines · 117 tokens per session scan A d17cccaea351

Subscribe to this mod's changes

agent-mvp is a skill published in the GitHub repository weiyi88/cc-code (5 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 2,688 once invoked, about $0.0001 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 2026-09-13.

Related

Other skills, from other repositories

Jira QA Workflows

Run QA work in Jira like a professional, bug lifecycle and triage, JQL queries for testers, quality dashboards, sprint QA rituals, and REST API automation for bulk bug operations and reporting.

PramodDutta/qaskills · 45 tokens

ai-team-orchestration

Bootstrap and run a multi-agent AI development team. Use when: starting a new software project with AI agents, setting up parallel dev/QA teams, creating sprint plans, writing brainstorm prompts with distinct agent voices, recovering a project workflow, or planning sprints.

boshi-xixixi/TraeSkill · 58 tokens

state-machine

Task lifecycle state transitions with validation gates. Defines states, triggers, and required proofs.

MadAppGang/claude-code · 20 tokens

subtask-update

Update subtask with fixes or new steps. Two trigger modes: (A) Auto-called by autoworker:gate-check on FAIL — reads FAIL info, adds supplementary steps. (B) User calls with a finding/bug during testing — diagnoses, fixes, updates subtask. Both modes end by invoking autoworker:dispatch to re-enter the loop.

phj128/autoworker · 77 tokens

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.

tae0y/python-project-template · 64 tokens

mutation-testing

Mutation testing patterns for verifying test effectiveness. Use when analyzing branch code to find weak or missing tests.

tae0y/python-project-template · 23 tokens