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/zhangshenao/harness9/prnpx skills add ZhangShenao/harness9 --skill prgit clone --depth 1 https://github.com/ZhangShenao/harness9Wrote 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/zhangshenao/harness9/pr)<a href="https://agentmods.dev/skills/zhangshenao/harness9/pr"><img src="https://agentmods.dev/badge/skills/zhangshenao/harness9/pr.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 5.1 | $0.00038 | $0.00777 |
| Opus 5 | $0.00019 | $0.00388 |
| Sonnet 5 | $0.00008 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
pr — Push & Pull Request
Overview
将本地提交推送到远程分支，并使用 gh CLI 创建 Pull Request，目标为仓库主分支。
默认行为：所有 PR 均以 Draft 模式创建（
--draft），避免误操作导致未经审查的代码被直接 merge。需要正式发起 Review 时，由用户在 GitHub 上手动将 Draft 转为 Ready for Review。
前置条件检查
- 确认本次对话中已执行过
/commit，且有新提交未推送 - 确认当前分支不是
main/master（若在主分支，停止并提示用户切换到功能分支） - 确认
ghCLI 已登录：gh auth status
执行步骤
1. 了解当前分支状态
git branch --show-current # 当前分支名
git log --oneline origin/HEAD..HEAD # 待推送的提交列表
git diff origin/HEAD...HEAD --stat # 本次 PR 涉及的文件变更
2. 确定目标分支
按以下顺序判断：
- 仓库默认分支（
gh repo view --json defaultBranchRef -q .defaultBranchRef.name） - 若无法获取，依次尝试
main→master - 仍不确定时，询问用户
3. 推送到远程
git push -u origin <当前分支名>
若远程已有同名分支且有分歧，不使用 --force，先告知用户手动处理冲突。
4. 起草 PR 内容
根据 git log 和 git diff 的输出，整理：
- 标题：70 字符以内，描述本次变更的核心目的
- 正文：包含变更摘要（2-4 条要点）和测试计划
5. 创建 Pull Request
始终使用 --draft 标志，避免误操作导致 PR 被直接 merge。
gh pr create \
--draft \
--base <目标分支> \
--title "<PR 标题>" \
--body "$(cat <<'EOF'
## Summary
- <要点 1>
- <要点 2>
## Test Plan
- [ ] <测试项 1>
- [ ] <测试项 2>
EOF
)"
禁止在 PR 正文中添加任何 AI 工具相关的标注，例如 🤖 Generated with Claude Code 或类似内容。
6. 输出结果
返回 PR URL，告知用户 PR 已创建成功。
常见错误
| 问题 | 处理 |
|---|---|
gh 未登录 |
提示用户执行 ! gh auth login |
| 当前分支无新提交 | 告知用户没有可推送的内容，建议先执行 /commit |
| 该分支已存在 PR | 使用 gh pr view 查看现有 PR，提示用户是否需要更新 |
| 推送被拒绝（non-fast-forward） | 不强制推送，提示用户检查远程分支状态 |
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.
- 5d ago First seen · 88 lines · 38 tokens per session scan A b8d675fecd0d
pr is a skill published in the GitHub repository ZhangShenao/harness9 (137 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 777 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…