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 skills add astordu/qoderharness --skill prgit clone --depth 1 https://github.com/astordu/qoderharnessWrote 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/skills/astordu/qoderharness/pr)<a href="https://agentmods.dev/skills/astordu/qoderharness/pr"><img src="https://agentmods.dev/badge/skills/astordu/qoderharness/pr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/astordu/qoderharness/pr"><img src="https://agentmods.dev/badge/skills/astordu/qoderharness/pr.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00044 | $0.01341 |
| Opus 5.5 | $0.00018 | $0.00536 |
| Sonnet 5.5 | $0.00009 | $0.00268 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
pr 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 23d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用以下结构撰写 PR Body:
## Summary
<图、diff 草图或树形结构>
## Evidence
- **Before:** <截图、输出或失败的测试>
**After:** <截图、输出或通过的测试>
## Merge Danger
**Door:** <one-way 或 two-way>
<可选:解释为什么>
**Blast Radius:** <用一个简短词组描述影响范围>
<可选:说明合并可能造成的影响>
通用要求
- 直接从
## Summary开始,不写前言。 - 保持文字简短;Reviewer 已经能看到 diff,PR Body 的任务是先让人看懂改动的形状、证据和风险。
- 优先使用仓库
GLOSSARY.md中的领域语言;没有该文件时沿用仓库和 issue 中的既有术语。 - 只描述实际 diff、真实测试结果和已知风险,不推测不存在的行为,不把“应该通过”写成“已经通过”。
Summary
选择能够说明关键变化的最小视图。可以使用一种,也可以组合少量几种;通常不应全部使用。
用伪代码展示逻辑或算法
保存内容
如果内容没有变化
返回缓存结果
写入新内容
返回最新结果
用调用树展示运行时控制流
submitForm
createSession
persistPrompt
launchAgent
navigateToSession
用组件树展示 UI 结构
保留与当前变化有关的状态、模块边界和文件位置:
<SessionPage> (apps/example/src/routes/session.tsx)
useSessionEvents()
<SessionToolbar>
<RunSkillButton> (packages/ui)
用浅层文件树展示职责变化或大范围重构
src/
├── commands/ # 解析用户操作
├── sessions/ # 管理会话状态
└── transport/ # 发送 API 请求
用 Mermaid 展示组件交互、控制流或数据流
sequenceDiagram
participant User
participant UI
participant Daemon
User->>UI: 选择命令
UI->>Daemon: 发送展开后的提示词
Daemon-->>UI: 流式返回结果
用 diff 草图突出结构变化
当读者已经了解原有结构,而重点是“哪里发生了变化”时使用 diff。
组件变化:
<SessionPage>
useSessionEvents()
<SessionToolbar>
+ <RunSkillButton />
<SessionTimeline>
+ <SkillResultCard />
文件布局变化:
src/
├── commands/
+│ └── show-me.ts # 展开斜杠命令
├── sessions/
-└── transport.ts
+└── transport/
+ ├── client.ts
+ └── stream.ts
调用树变化:
submitForm
createSession
persistPrompt
+ expandSkillMention
launchAgent
- navigateToSession
+ navigateToSession
+ subscribeToEvents
状态或控制流变化:
保存内容
- 写入内容
+ 如果内容没有变化
+ 返回缓存结果
+ 写入内容
+ 使缓存失效
必要时展示完整目标代码块
当大部分内容都是新增的、缺少上下文会掩盖职责或顺序,或者读者需要可复制的目标形状时,展示完整代码块:
function expandSkill(command: string): string {
const skillName = command.slice(1);
return `use the ${skillName} skill`;
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago First seen · 191 lines · 44 tokens per session scan A 3faec04804ee
pr is a skill published in the GitHub repository astordu/qoderharness (38 stars, last pushed 23d ago), licensed MIT. It adds 44 tokens to every session and 1,341 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-05.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…