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 instructions/xiaozhi86/qamaster/agents-mdgit clone --depth 1 https://github.com/xiaozhi86/qamasterWrote 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/instructions/xiaozhi86/qamaster/agents-md)<a href="https://agentmods.dev/instructions/xiaozhi86/qamaster/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaozhi86/qamaster/agents-md.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 | $0.00655 | $0.00655 |
| Opus 5 | $0.00328 | $0.00328 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
qamaster AGENTS.md 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.
What it actually says
QA Master — Codex 项目指令
本仓库提供两个 QA 能力，skill 正文统一存放在 skills/ 下（单一事实源），采用薄引用方式调用：运行时读取对应 SKILL.md 并以其所在目录为 skill 根（references/、scripts/、config/ 均相对它解析），不复制正文。
能力入口
- case-design（测试用例设计）：用户提到测试用例设计 / 用例生成 / 需求转用例 / 用例转 Excel / 覆盖分析时 → 读取并执行
skills/case-design/SKILL.md。 - requirement-review（需求评审）：用户提到需求评审 / 需求分析 / 多角色评审时 → 读取并执行
skills/requirement-review/SKILL.md。
也可通过自定义 prompt 触发：把 codex/prompts/*.md 拷贝到 ~/.codex/prompts/，即可用 /case-design、/requirement-review。
Runtime（可选增强，Claude Code 默认启用）
runtime/qamaster_runtime.py 是 case-design 的流程状态机（0-14 阶段严格顺序 + 质量门禁 + 人工确认点，模型无关）。Codex 下若能执行 Python，可先用 bootstrap（派生需求标识）再 start --req-id <需求标识> 启动受控流程；不用 Runtime 时退回 skills/case-design/SKILL.md 的 15 阶段定义执行，业务规则完全一致。同一工程可并行处理多个需求：状态按 (workflow, req_id) 分区互不干扰。
产出位置
- case-design → 项目根的
case-design-out/（自动创建）；Runtime 控制层状态在.qamaster/case-design/<需求标识>/state.json（按需求标识分区隔离，多需求互不覆盖）。case-design-out/MANIFEST.md为多需求共享索引，由 Runtime 在 gate PASS 时自动维护。 - requirement-review → 项目根的
requirement-review-out/（自动创建）；Runtime 控制层状态在.qamaster/requirement-review/<需求标识>/state.json（按需求标识分区隔离，多需求互不覆盖）。
依赖
- Python 3.7+：case-design 的回读校验脚本在
skills/case-design/scripts/；Runtime 在runtime/；生成 Excel 需openpyxl（缺失时 skill 会自动尝试安装并兜底报错）。 - skill 正文中 Claude Code 专属建议（
CLAUDE_CODE_MAX_OUTPUT_TOKENS、.claude/settings.json、acceptEdits）在 Codex 无对应物，忽略即可；等价行为用 Codex 自身配置实现。
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 · 25 lines · 655 tokens per session scan A 4858ca596c12
qamaster AGENTS.md is an instructions file published in the GitHub repository xiaozhi86/qamaster (4 stars, last pushed 9d ago), licensed MIT. It adds 655 tokens to every session, about $0.0033 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 instructions, from other repositories
webqa-agent CLAUDE.md
Instructions for MigoXLab/webqa-agent, covering claude.md, 模块化规则引用, 研究和规划 (critical), 1. 使用 context7 mcp 工具 and 2. 使用联网搜索.
hoop CLAUDE.md
Claude Code instructions for hoophq/hoop, covering claude.md, project overview, toolchain & prerequisites, architecture and module breakdown.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
rome CLAUDE.md
Claude Code instructions for rome-os/rome, covering rome, playbook and traps.
zapcode CLAUDE.md
Instructions for TheUncharted/zapcode, covering claude.md, git, read agents.md first, codebase orientation and how to add a new language feature.
MathModelAgent CLAUDE.md
Claude Code instructions for jihe520/MathModelAgent, covering claude.md, 项目概述, commands, 后端 and 安装依赖.