qa-skills AGENTS.md

qa-skills AGENTS.md is an instructions file for Codex, OpenCode from fishzjp/qa-skills. It costs 946 tokens per session, scanned A, original, MIT.

Project instructions for qa-skills, a collection focused on improving software testing by repeatedly evaluating and refining its guidance.

In plain words
What is it for?
Use them when maintaining qa-skills, reviewing evaluation results, organizing regression tests, or deciding whether a change is worth keeping.
Why use it?
They give maintainers a process for finding weak spots, checking changes across models, and using real failures to improve the project.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/fishzjp/qa-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/fishzjp/qa-skills

Made for: Codex, OpenCode.

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 qa-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fishzjp/qa-skills/agents-md.svg)](https://agentmods.dev/instructions/fishzjp/qa-skills/agents-md)
Your own site
<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>
Per session 946 This file is loaded in full into every session.
When invoked 946 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00946 $0.00946
Opus 5 $0.00473 $0.00473
Sonnet 5 $0.00189 $0.00189
Haiku 4.5 $0.00095 $0.00095

Measured yesterday against content hash b472e5a393e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 52 lines

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/)

  1. 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
  2. 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)。
  3. 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)。

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. yesterday Changed · +19 tokens per session b472e5a393e9
  2. 5d ago First seen · 52 lines · 927 tokens per session scan A 89e9542d7e04

Subscribe to this mod's changes

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.