Conservative Code Edits Agent Skill

Enforces minimal, safe code modifications to prevent unnecessary refactoring and protect core project architecture.

Context cost
4.3k tokensestimated from the bundle, loaded when it triggers
Bundle
8 files · 18.4 kB1 script among them — read before you run
Licence
Apache-2.0the author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

修改现有项目代码时强制执行保守策略,最小化改动、保留既有架构与风格、规避无关重构及共享代码风险。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

productivityrefactoring

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md1.5 kB · preview
--- name: conservative-code-edits ---
5## 编码原则
6
7- 使用最小必要改动完成任务,只修改与任务直接相关的代码。
8- 默认保持现有架构、交互逻辑、状态流转、模块职责、命名风格和实现模式。
9- 不做无关重构、格式化、优化或清理;不删除改动前已存在的无关旧代码。
10- 修改前关注影响范围,修改后尽可能验证结果
11- 简洁优先,避免过度复杂、臃肿抽象
12- 在完成代码修改后,不要执行编译操作
13- 在生成回答时,请使用自然、流畅的中文表达,避免生硬的翻译腔
14- 对于新增的方法以及关键逻辑位置,必须添加通俗易懂的注释,确保代码意图清晰明了。
15
16## 项目硬性规则
17
18- 如需修改架构、交互逻辑、状态流转、模块职责或核心实现风格,必须先说明原因、影响范围和风险,并等待确认。
19- 如需修改公共基础代码,必须先列出影响范围并等待确认。公共基础代码包括:基类、公共 UI 组件、公共工具类、网络层、存储层、路由、日志、埋点、权限、主题等。
20- 如果项目已支持深色模式,禁止硬编码固定 UI 颜色;颜色必须动态适配,并优先使用现有颜色资源
21
22## 优先级
23
24用户明确要求 > 项目硬性规则 > 编码原则。
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md43 words
Files8
LicenceApache-2.0
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈20
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
4,330
on trigger
The instruction body and 7 supporting files, read only when the skill fires.
2.2%
of a 200k window
Ten skills this size would take about 22% of the window before you open a file.
050k100k150k200k context window

4.3k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

8 files, 18.4 kB on disk. Mostly text — the instructions the model reads — with 1 script in it that your client would run only if the instructions tell it to.

  • SKILL.md1.5 kB
  • cordis.patch.yml0.1 kB
  • index.mjs1.0 kB
  • LICENSE.txt10.8 kB
  • package.json0.4 kB
  • README.md2.0 kB
  • README.zh.md2.3 kB
  • skills.sh.json0.3 kB
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 1 script beside the text, so the bundle is 8 files you can review in full before installing. The Apache-2.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Conservative Code Edits · 4.3k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/conservative-code-edits/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/conservative-code-edits" ] && { [ ! -e .claude/skills/conservative-code-edits ] || { mv .claude/skills/conservative-code-edits "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/conservative-code-edits" .claude/skills/ && echo "Installed .claude/skills/conservative-code-edits"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add addxing/conservative-code-edits

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/conservative-code-edits/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/conservative-code-edits/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/conservative-code-edits" ] && { [ ! -e ~/.claude/skills/conservative-code-edits ] || { mv ~/.claude/skills/conservative-code-edits "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/conservative-code-edits" ~/.claude/skills/ && echo "Installed ~/.claude/skills/conservative-code-edits" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/conservative-code-edits/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceaddxing/conservative-code-edits

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

AD
addxing

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill