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 skills add weiyi88/cc-code --skill agent-whole-qagit 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/agent-whole-qa)<a href="https://agentmods.dev/skills/weiyi88/cc-code/agent-whole-qa"><img src="https://agentmods.dev/badge/skills/weiyi88/cc-code/agent-whole-qa/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.
<a href="https://agentmods.dev/skills/weiyi88/cc-code/agent-whole-qa"><img src="https://agentmods.dev/badge/skills/weiyi88/cc-code/agent-whole-qa.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.04757 |
| Opus 5.5 | $0.00010 | $0.01903 |
| Sonnet 5.5 | $0.00005 | $0.00951 |
| Haiku 4.5 | $0.00003 | $0.00476 |
Grade A, and why
agent-whole-qa 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 1mo 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-whole-qa — 全量验收 + 修复闭环编排器
与
qaagent 的关系:qa是「单模块测一次」的原子能力;本 skill 是「全模块 × 多轮 + 修复回环」的编排层,复用qa,不重写测试逻辑。 与agent-mvp的关系:agent-mvp每阶段用qa做增量验收;本 skill 用于 MVP 收口前的一次性全量清算。
⛔ 六条硬约束(违反任一即本次验收无效)
1. 你是编排器,不是执行者
❌ 错:agent-whole-qa 自己测、自己修
→ 测的人知道修的人怎么想,修的人知道测的人怎么测 → 互相糊弄
✅ 对:agent-whole-qa 只做 清点 / 分发 / 汇总 / 循环控制
agent-whole-qa(不碰代码,不碰需求)
├─ Agent(subagent_type=qa) ──► 测(只拿到断言,不知道谁会修)
└─ Agent(subagent_type=dev) ──► 修(只拿到 FAIL 清单,不知道怎么测的)
主控绝不自己写测试、自己改代码。发现自己在写 expect(...) 或改 src/ 就是越界了。
2. 分母先锁定,再开测
INVENTORY 阶段的产物落盘后本轮分母不可变更。禁止中途以「这个按钮不用测」「这个接口是内部的」为由缩小分母。要改分母,只能作废本轮重新开始。
3. 禁止修需求
本 skill 及其派生的 dev subagent 对以下文件【只读,绝对禁写】:
active/prd.md active/ux.md active/api.md
修不动 → 标记 ESCALATE 交人决策
这是 AI 修 bug 时最常走的偷懒路径:改断言让测试变绿。不用规则堵死,它一定会走。
4. 收敛门控
第 N 轮 FAIL 数 必须 < 第 N-1 轮 FAIL 数
├─ 不递减 → 停止,报告「未收敛」,交人决策
├─ 出现新增 FAIL → 停止(修 A 坏 B),报告震荡点,建议回滚本轮
└─ 最多 3 轮
5. 回归门(每轮必跑)
每轮修完,重跑范围 = 本轮 FAIL 项 + affected 算出的真实影响面
↑ 缺这半段就会「越修越坏」而毫不知情
⭐0.10.0:影响面从「同模块已 PASS 项」升级为 codegraph affected 算出的
传递闭包 —— 同模块是人凭直觉画的圈,affected 是沿 import 图算出的事实,
跨模块的隐式依赖只有后者抓得到。
codegraph affected <本轮修改的源文件...>
非 .spec/.test 命名的测试补跑 --filter "<project.md §六 登记的 glob>"
返回空 → 报一行「未匹配到测试,本轮用全量」+ 自查三点:
① 测试代码是否被 .gitignore 屏蔽(被 ignore 则不进索引)
② 测试是否 import 被测源码(纯 HTTP 型无 import 边,追不到)
③ 命名是否需 --filter
CLI 未装 → 静默退回「同模块已 PASS 项」,不报
6. 禁止静默截断
未测的元素/接口/断言,必须逐条列入 SKIPPED 并给原因。同构重复元素若做了组内抽样,必须写明「同构组 N 个,实测 M 个」—— 报告里出现「全部覆盖」而分母被悄悄缩小,是最严重的失职。
生命周期总览
┌ ⓿ PREFLIGHT 前置检查 ──────────────────────────────────────────┐
│ .cc_code/ 存在 · prd.md 有模块清单与验收断言 · 应用能起来 │
└───────────────────────┬────────────────────────────────────────┘
▼
┌ ❶ INVENTORY 清点(主控,只做一次,落盘即锁死分母)─────────────┐
│ 路由发现 → 页面 P[] │
│ ux.md §2.4 声明 ∪ 逐页 DOM snapshot → 元素 E[] ⭐取并集,差集必报│
│ 接口发现 → 接口 A[] │
│ prd.md §1.5 主表 → 断言 ASSERT[] │
│ ux.md §2.3 U编号矩阵 → 五态判定项 USTATE[] │
│ 按 prd.md 模块清单分组 → 模块 M[] │
│ codegraph 扫冗余 → DEAD/ORPHAN/DUP[] │
│ ↓ 落盘 .cc_code/docs/qa/<日期>-inventory.md │
└───────────────────────┬────────────────────────────────────────┘
▼
┌ ❷ FAN-OUT 分模块并发(每模块 1 个 qa subagent,独立上下文)────┐
│ 模块 M1 ──► 逐元素点击 + 五态断言 + 截图 + console 捕获 │
│ 模块 M2 ──► 同上 (并发,单消息多 Agent) │
│ 接口批 ──► 每接口 5 类断言 │
│ 每个只回 {断言ID+中文模块-功能, verdict, 证据, 复现步骤} │
└───────────────────────┬────────────────────────────────────────┘
▼
┌ ❸ REDUCE 汇总(主控)────────────────────────────────────────┐
│ 四个分母各算覆盖率:A断言 / U五态 / 元素 / 接口 │
│ SKIPPED 逐条列明原因 │
│ ↓ 落盘 docs/qa/<日期>-round-N.md │
│ ↓ gates.md 就地更新矩阵对应行 ⛔禁新开轮次章节 │
└───────────────────────┬────────────────────────────────────────┘
▼
┌─ 全 PASS ─► ❺ 收口
│
└─ 有 FAIL ─┐
▼
┌ ❹ FIX 轮(dev subagent,独立上下文)──────────────────────────┐
│ 输入:FAIL 清单原文(不含测法细节,防针对性糊弄) │
│ 禁写:prd.md / ux.md / api.md │
│ 修不动 → ESCALATE │
│ ↓ 回归门:重跑 FAIL + 同模块已 PASS │
│ ↓ 收敛检查(约束 4)→ 通过则回 ❸,否则停止交人 │
└────────────────────────────────────────────────────────────────┘
▼
┌ ❺ 收口 ──────────────────────────────────────────────────────┐
│ gates.md 矩阵定稿 · back_up/milestone-log.md +1行 · status.md 刷新坐标 │
└────────────────────────────────────────────────────────────────┘
What ships with it
4 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.
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.
- 1mo ago Changed · -99 tokens per session c6a329396b8d
- 1mo ago First seen · 289 lines · 125 tokens per session scan A a765fa9a9993
agent-whole-qa is a skill published in the GitHub repository weiyi88/cc-code (5 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 4,757 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.
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.
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.
state-machine
Task lifecycle state transitions with validation gates. Defines states, triggers, and required proofs.
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.
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.