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/fishzjp/qa-skills/agents-mdgit clone --depth 1 https://github.com/fishzjp/qa-skillsWrote 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/fishzjp/qa-skills/agents-md)<a href="https://agentmods.dev/instructions/fishzjp/qa-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/fishzjp/qa-skills/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 | $0.00946 | $0.00946 |
| Opus 5 | $0.00473 | $0.00473 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
qa-skills 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 yesterday.
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
AGENTS.md — qa-skills 项目指令
本文件是维护者的迭代 SOP。"评测三轨道"及各处
eval/引用描述的是本地维护的评测链路 (2026-08-22 起不随公开仓库分发,公开仓库只含 skills 产品内容);公开侧证据链为每版 Release 附带的增益矩阵快照。
使命(所有工作的对齐点)
安装 qa-skills 之后,对任何 agent、任何模型,在软件测试领域带来质的提升。 一切决策——改 skill、建评测、扩任务、发版本——的优先级判断都以这一句话为锚。
战略路径:迭代飞轮
skill bench 是驱动 qa-skills 迭代的手段,不是目的。标准回路:
跑 bench → 失败模式归类、定位 skill 短板 → 修改 skill → 复验(评测-修复闭环)
bench 的产出是"改哪里",不是总分。聚合数字(如覆盖 +8.7pp)用于发布,不用于指导迭代; 指导迭代的是逐 GT 点的失败明细及其归类(澄清缺失 / 边界遗漏 / 状态遗漏 / 断言强度不足 → 映射到 skill 的具体环节)。
北极星指标
跨模型 × 跨宿主的 On/Off 增益下限(min,不是均值)。
- 弱模型段位:追求可执行性、真实执行通过率等类别性质变(0.2→0.98 型)
- 强模型段位:覆盖增益趋零后,价值在流程纪律与系统行为(复审拦截、回归编排、接口一致)
- 对单一模型(当前 glm-5.2)迭代出的提升若不能跨模型复现,视为过拟合而非进步
评测三轨道(eval/)
- 模型矩阵(常设回归):标准回路固定 2–3 个段位的便宜模型(flash 级 + 中档), 强模型按里程碑跑。skill 修改的合入门槛之一:最弱模型上的增益不回退。
- in-situ 轨道:真实宿主会话中量三个数——触发正确率、装载文件集合、产出质量。 这是"任何 agent"的关键证据(注入式评测只证明内容值得装,不证明装了会生效)。
- 注入式轨道(现有 harness):内容质量哨兵,原样保留。
迭代纪律
- 只有类别性 / 大效应信号才触发 skill 变更;+2pp 级差异一律视为采样噪声 (n=3 的采样方差与单次普通修改的效应同量级,见澄清任务跨轮方向翻转案例)。
- 任务池轮换(30–50 任务抽半跑,季度换血),防 skill 对着题库优化。
- 迭代涉及的任务做双人 GT 复核——GT 错标会让飞轮朝错误方向持续优化,是最危险的失败模式。
- 日常真实使用中的触发失败 / 产出不佳案例,每周沉淀 2–3 个进任务池(dogfooding 反哺)。
- 每版 Release 配增益矩阵快照(跨模型 On/Off 对比)与迭代记录——这是 skill bench 的自然形态, 也是"安装这个 skill 会发生什么"的纵向证据。
报告与对外发布的定位
评测报告(eval/reports/)是里程碑快照,不是目标本身。对外数字发布前跑零成本污染三件套 (cutoff 核对 / n-gram 扫描 / canary),见本地维护的 eval/harness/CONTAMINATION.md(eval/ 为本地链路,不随公开仓库分发)。
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.
- yesterday Changed · +19 tokens per session b472e5a393e9
- 5d ago First seen · 52 lines · 927 tokens per session scan A 89e9542d7e04
qa-skills AGENTS.md is an instructions file published in the GitHub repository fishzjp/qa-skills (22 stars, last pushed 2d ago), licensed MIT. It adds 946 tokens to every session, about $0.0047 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 2026-08-30.
Other instructions, from other repositories
quality-skills AGENTS.md
Instructions for aks-builds/quality-skills, covering agents.md, repository overview, repository structure, agent skills specification and required frontmatter.
proctor AGENTS.md
Instructions for OrionArchitekton/proctor, covering agents.md — proctor, repo role, layout, start here and validation.
quality-skills CLAUDE.md
Instructions for aks-builds/quality-skills: See AGENTS.md for guidelines on working in this repository.
cursor-mcp-qa-agent AGENTS.md
AGENTS.md instructions for Ardaka/cursor-mcp-qa-agent, covering project instructions, purpose, commands and guardrails.
qualflare-claude-code CLAUDE.md
Claude Code instructions for Qualflare/qualflare-claude-code, covering qualflare-ai — claude code plugin developer guide, what is this?, plugin structure, how to update skills or commands and keeping framework slugs in sync.
cli AGENTS.md
AGENTS.md instructions for qawolf/cli, covering @qawolf/cli — agent instructions, commands, testing, project structure and code style.