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 commands/xiaozhi86/qamaster/case-designgit 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/commands/xiaozhi86/qamaster/case-design)<a href="https://agentmods.dev/commands/xiaozhi86/qamaster/case-design"><img src="https://agentmods.dev/badge/commands/xiaozhi86/qamaster/case-design.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 | $0.00039 | $0.01790 |
| Opus 5 | $0.00019 | $0.00895 |
| Sonnet 5 | $0.00008 | $0.00358 |
| Haiku 4.5 | $0.00004 | $0.00179 |
Grade A, and why
case-design 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
启动 qamaster Runtime 受控流程(模型负责思考,Runtime 负责控制——流程状态由 Python 状态机裁决,任何模型不可绕过)。
路径解析(先做·一次)
本命令文件位于 plugin 根目录的 commands/ 下,Runtime 位于同级 ../runtime/。候选列表存在性探测(v0.6.0 修复:单一 $0 推导在 marketplace 缓存安装下会打错路径):
# 有序候选:逐一 [ -f ] 探测,取第一个命中
PLUGIN_ROOT=""
for c in \
"$(cd "$(dirname "$0")/.." 2>/dev/null && pwd)" \
"$HOME/.claude/plugins/qamaster" \
$(ls -d "$HOME"/.claude/plugins/cache/qamaster/qamaster/*/ 2>/dev/null | sort -V | tail -1) \
"D:/qamaster" \
; do
[ -n "$c" ] && [ -f "${c%/}/runtime/qamaster_runtime.py" ] && PLUGIN_ROOT="${c%/}" && break
done
echo "PLUGIN_ROOT=$PLUGIN_ROOT"
- 候选 4 为本地开发仓库路径,按实际克隆位置调整;候选 3 为 marketplace 缓存安装(glob 取版本号最大者)。
- 全部候选未命中 → 判定"Runtime 未安装":允许进入薄客户端降级(SKILL.md Runtime 控制协议·情形A,带降级最低门禁)。
- 候选命中但执行报错(如 Bash 分类器暂不可用)→ 判定"Runtime 存在但调用失败":禁止降级,按 SKILL.md 降级协议情形B 退避重试,仍失败则暂停流程、不得落盘 TestCases。
第一步:启动 Runtime(bootstrap → start,必须先做·单步不变对用户透明)
cd "<用户当前项目根>"
# 1) bootstrap 派生 req_id(不创建状态·幂等可重跑);检测到在途状态输出 RESUME
REQ_ID=$(python "$PLUGIN_ROOT/runtime/qamaster_runtime.py" bootstrap \
--workflow case-design --user-input "$ARGUMENTS" --workdir "$(pwd)" \
| sed -n 's/.*req_id=\([^ ]*\).*/\1/p' | head -1)
# bootstrap 输出 BOOTSTRAP RESUME req_id=<id> 时 REQ_ID 同样取到该 id(复用,不重建状态)
# 2) start 按 (workflow, req_id) 创建/续跑状态(状态落 .qamaster/case-design/<req_id>/)
python "$PLUGIN_ROOT/runtime/qamaster_runtime.py" start \
--workflow case-design --req-id "$REQ_ID" --workdir "$(pwd)"
- cwd 必须是用户项目根(产出物写
./case-design-out/,状态写./.qamaster/case-design/<req_id>/)。 req_id由 bootstrap 派生(文件取首个#标题清洗 / 内联取首个非空行;去重,碰撞加-YYYYMMDD),模型不在阶段内派生 id——消除"先有鸡还是先有蛋"。bootstrap 若失败(空 id 等),停下报错指引,不得跳过。- 输出含【RUNTIME CONTRACT 契约卡】:先按其提示一次性阅读全局业务规范
skills/case-design/SKILL.md(避坑红线/输入协议/运行模式),随后回到契约卡执行当前 Phase。 - 已存在进行中的同一 req 时,bootstrap 输出
RESUME→start走 resume 分支断点续跑(恢复契约卡,不重置)——分区路径即 resume 判据,不同需求各自续跑互不干扰。
第二步:按契约卡执行当前 Phase
每阶段只做契约卡 ALLOWED 中的事,产物达标后:
python "$PLUGIN_ROOT/runtime/qamaster_runtime.py" gate --workflow case-design --req-id "$REQ_ID" # 出口门禁(机器判定,禁止自证)
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 · 86 lines · 39 tokens per session scan A bb9ed8444a4c
case-design is a command published in the GitHub repository xiaozhi86/qamaster (4 stars, last pushed 9d ago), licensed MIT. It adds 39 tokens to every session and 1,790 once invoked, about $0.0002 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 commands, from other repositories
MIGRATE_DESIGN
Design doc for the migration tool PR. Author: Sol ([email protected]). Co-authored-by: wakesync.
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
commit
智能生成 Git 提交信息并提交.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
bug-check
Run automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
release
Create a new release for the Starpod workspace.