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 skills/astordu/qoderharness/code-reviewnpx skills add astordu/qoderharness --skill code-reviewgit clone --depth 1 https://github.com/astordu/qoderharnessWhat 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 | $0.00119 | $0.01964 |
| Opus 5 | $0.00060 | $0.00982 |
| Sonnet 5 | $0.00024 | $0.00393 |
| Haiku 4.5 | $0.00012 | $0.00196 |
Grade A, and why
code-review 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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
对 HEAD 与用户提供的固定基点之间的 diff 进行双维度审查:
- 规范(Standards) —— 代码是否符合本仓库有文档记录的编码规范?
- 需求(Spec) —— 代码是否忠实地实现了最初发起的 issue / PRD / 规格说明?
两个维度都作为并行子代理运行,以免相互污染各自的上下文,随后由本技能汇总它们的发现。
issue 追踪器应当已提供给你 —— 如果 docs/agents/issue-tracker.md 缺失,请运行 /init_goder_harness。
流程
1. 确定固定基点
用户所说的即为固定基点 —— 一个提交 SHA、分支名、标签、main、HEAD~5 等。如果他们没有指定,就询问。
一次性确定 diff 命令:git diff <fixed-point>...HEAD(三点写法,因此比较是针对 merge-base 进行的)。同时通过 git log <fixed-point>..HEAD --oneline 记录提交列表。
在继续之前,确认固定基点可以解析(git rev-parse <fixed-point>)且 diff 非空。错误的引用或空 diff 应当在此处就失败 —— 而不是在两个并行子代理内部才失败。
2. 确定需求来源
按以下顺序查找最初发起的规格说明:
- 提交信息中的 issue 引用(
#123、Closes #45、GitLab 的!67等)—— 通过docs/agents/issue-tracker.md中的工作流获取。 - 用户作为参数传入的路径。
- 位于
docs/、specs/或.scratch/下、与分支名或特性相匹配的 PRD/规格说明文件。 - 如果什么都没找到,就询问用户规格说明在哪里。如果他们说没有,需求 子代理将跳过并汇报“无可用规格说明”。
3. 确定规范来源
仓库中任何记录代码应如何编写的内容,例如 CODING_STANDARDS.md 或 CONTRIBUTING.md。
在仓库所记录内容的基础之上,规范维度始终携带下方的坏味道基线(smell baseline)—— 一组固定的 Fowler 代码坏味道(《重构》第 3 章),即便某个仓库什么都没记录也依然适用。有两条规则约束它:
- 仓库优先。 有文档记录的仓库规范始终胜出;当它认可某个基线本会标记的做法时,抑制该坏味道。
- 始终是主观判断。 每个坏味道都是带标签的启发式(“可能的 Feature Envy”),绝非硬性违规 —— 并且,如同这里的任何规范一样,跳过工具已经强制执行的部分。
每个坏味道遵循 它是什么 → 如何修复;将其与 diff 对照:
- Mysterious Name(神秘命名) —— 名称无法揭示其作用或持有内容的函数、变量或类型。→ 重命名;若找不到诚实的名字,说明设计混浊。
- Duplicated Code(重复代码) —— 相同的逻辑形态出现在改动的多个代码块或文件中。→ 提取共享形态,从两处调用。
- Feature Envy(依恋情结) —— 某方法访问其他对象的数据多于访问自身的数据。→ 将该方法移动到它所依恋的数据上。
- Data Clumps(数据泥团) —— 相同的几个字段或参数总是结伴出现(一个想要诞生的类型)。→ 将它们捆绑为一个类型并传递之。
- Primitive Obsession(基本类型偏执) —— 用基本类型或字符串来代表本该拥有自己类型的领域概念。→ 给该概念一个自己的小类型。
- Repeated Switches(重复的 switch) —— 相同的
switch/if级联在改动中反复出现于同一类型上。→ 用多态替换,或用两处共享的一张 map。 - Shotgun Surgery(霰弹式修改) —— 一个逻辑改动迫使 diff 中许多文件出现分散的编辑。→ 把一起变化的内容聚拢到一个模块中。
- Divergent Change(发散式变化) —— 一个文件或模块因几个不相关的原因被编辑。→ 拆分,使每个模块只因一个原因而变化。
- Speculative Generality(夸夸其谈通用性) —— 为规格说明并不需要的需求而添加的抽象、参数或钩子。→ 删除它;内联回去,直到出现真实需求。
- Message Chains(过长的消息链) —— 调用方不应依赖的长串
a.b().c().d()导航。→ 将这段游走隐藏到第一个对象上的一个方法背后。 - Middle Man(中间人) —— 一个大部分只是向下委托的类或函数。→ 去掉它,直接调用真正的目标。
- Refused Bequest(被拒绝的遗赠) —— 一个忽略或覆盖了其继承的大部分内容的子类或实现类。→ 放弃继承,改用组合。
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.
- 2d ago First seen · 90 lines · 119 tokens per session scan A 2b7e0665e82f
code-review is a skill published in the GitHub repository astordu/qoderharness (21 stars, last pushed 7d ago), licensed MIT. It adds 119 tokens to every session and 1,964 once invoked, about $0.0006 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…