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/pingfanfan/hello-dsh/refactor-safelynpx skills add pingfanfan/hello-dsh --skill refactor-safelygit clone --depth 1 https://github.com/pingfanfan/hello-dshWrote 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/pingfanfan/hello-dsh/refactor-safely)<a href="https://agentmods.dev/skills/pingfanfan/hello-dsh/refactor-safely"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/refactor-safely.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 | $0.00054 | $0.00971 |
| Opus 5 | $0.00027 | $0.00485 |
| Sonnet 5 | $0.00011 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
refactor-safely 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
安全重构
重构的定义：改变代码结构，不改变外部行为。
一旦掺进了行为变更，它就不再是重构，出问题时也无法用「行为应该完全一样」来定位。这是这件事唯一的纪律。
开始之前
三个前置条件，缺一个就先补：
- 有能验证行为不变的手段 —— 测试、快照、或一段能对比输出的脚本。没有就先写，这不是浪费时间，是重构的唯一安全网。
- 工作区是干净的 —— 重构的 diff 必须只包含重构。
- 说得清为什么要改 —— 「这样更好看」不算理由。真实理由通常是：这里要加功能但加不进去、这段重复已经导致过 bug、这个函数没人敢动。
说不清理由就不要动。 没有具体痛点驱动的重构，是在用风险换取审美。
小步前进
每一步都要满足：改完立刻能验证，验证失败能立刻回退。
一步的合理大小：
- 提取一个函数
- 重命名一个符号
- 移动一个函数到另一个文件
- 内联一个只用一次的变量
不合理的一步：
- 「把这个模块重新组织一下」
- 「顺便把命名统一了」
每步之后跑验证。不要攒着一起验。 攒了三步再跑，失败时你不知道是哪步的问题，而这三步之间往往互相依赖，回退也变难。
常见重构的顺序
提取函数：先复制代码到新函数，参数用原地变量名，跑通；再把原处替换成调用；最后清理参数名。不要一步到位。
拆分大文件：先把要移走的部分整块移动，import 补上，验证；再调整命名和接口。移动和改造分开做。
消除重复：先确认这两处真的是同一件事，不是长得像。长得像但会独立演化的代码，合并之后会变成带一堆 flag 的函数，比重复更糟。
改接口：先加新的，让新旧并存并验证；再逐个迁移调用方；最后删旧的。三次提交，不是一次。
什么时候停
- 验证挂了，且十分钟内没定位到原因 —— 回退这一步，重新想
- 发现需要改行为才能继续 —— 停下，把行为变更单独提出来做，做完再回来重构
- 改动范围开始扩散 —— 说明这一步太大了，回退，切小
回退不是失败。 在重构里回退是廉价的，卡在半途才是昂贵的。
提交
重构和功能修改必须分开提交。
判断标准：这两部分能不能单独回退？ 不能就说明混在一起了，该拆。
提交信息用 refactor: 前缀，正文说清楚为什么要改：
refactor(session): 把事件投影从 SessionStore 里拆出来
SessionStore 现在同时负责持久化和投影，加新的事件类型时两处都要
改，已经漏过一次。拆开之后投影逻辑可以单独测。
行为不变，投影结果的快照测试全部通过。
最后那句「行为不变 + 怎么验证的」是重构提交该有的东西。
不要做的事
- 不要在重构的同时修 bug，哪怕顺手
- 不要在重构的同时改格式（格式化单独一个提交）
- 不要引入新抽象，除非当前的重复已经造成了具体问题
- 不要在没有验证手段的情况下动手
- 不要一次改超过你能一眼看完的量
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 · 82 lines · 54 tokens per session scan A 52cb8a570951
refactor-safely is a skill published in the GitHub repository pingfanfan/hello-dsh (88 stars, last pushed 22d ago), licensed MIT. It adds 54 tokens to every session and 971 once invoked, about $0.0003 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
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
dsh-web-release
Release and publish the dsh-web monorepo (DSH Web GUI plugin family + skin collection) — bump all packages to one unified version, commit and tag (tags are cut from main after dev integration; dev is the integration branch), push the vX.Y.Z tag that triggers the GitHub Actions publish pipeline, and verify the npm…
dsh-web-community-plugin-developer
Develop a DSH community plugin and register it in the dsh-web Community Plugins index — author the plugin in the contributor's own repository following the official cordis bundle standard, add its entry to packages/dsh-community-plugins/community.json, regenerate the index with scripts/community-index, rebuild and…
dsh-web-skin-developer
Build a new skin for the dsh-web skin collection (DSH Web GUI) and publish it into the Skin Center — the first-level settings section — scaffold with scripts/dsh-skin-new, author the v2 skin.json manifest plus skin.css token remap (pure asset directory, no package.json, no build step), validate with scripts/dsh-skin…
dsh-web-pre-push-checks
Use before pushing, opening or updating a pull request, or claiming dsh-web checks pass. Selects the required repository gates and diff-specific generation, build, and GUI evidence.
dsh-web-documentation
Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.