csswitch-change-checks

A guide for choosing limited checks after changing CSSwitch source code, tests, or Markdown files. It distinguishes quick in-progress checks from checks for a committed change range.

In plain words
What is it for?
Use it to select and report tests or other checks, identify changed file layers, state what was not run, and assess CSSwitch changes against their owning checks.
Why use it?
It helps report the relevant risk and evidence without overstating a focused check as proof that all source code is correct.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/superjj007/csswitch/csswitch-change-checks
Any agent
npx skills add SuperJJ007/CSSwitch --skill csswitch-change-checks
Clone the repo
git clone --depth 1 https://github.com/SuperJJ007/CSSwitch

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 246 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00246
Opus 5 $0.00015 $0.00123
Sonnet 5 $0.00006 $0.00049
Haiku 4.5 $0.00003 $0.00025

Measured 3d ago against content hash 52576da1b487, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

csswitch-change-checks 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 3d 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.

.agents/skills/csswitch-change-checks/SKILL.md · 13 lines

What it actually says

CSSwitch change checks

Use this Skill to select and report checks after an implementation, test, or documentation change. Read 代码作者规则, 开发, and 自动测试 before selecting evidence.

  • In quick WIP mode, work from the requester’s declared goal and changed paths. Report the highest F0F3 risk, scope, suggested owning checks, evidence layer, and items not run. Do not guess a base or read untracked-file contents.
  • In candidate or committed-range mode, require the requester to supply base and head. Report the resolved base, head, merge-base, and the committed, staged, unstaged, and untracked path layers; list untracked paths only.
  • Do not turn a static-mapping miss into a lower risk. A focused PASS is not SOURCE-GREEN; use the single source-closure gate only under the conditions in the linked operations.
Changes

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.

  1. 3d ago First seen · 13 lines · 30 tokens per session scan A 52576da1b487

Subscribe to this mod's changes

csswitch-change-checks is a skill published in the GitHub repository SuperJJ007/CSSwitch (452 stars, last pushed 11d ago), licensed MIT. It adds 30 tokens to every session and 246 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.

Related

Other skills, from other repositories

vision-multimodal

给 DeepSeek 这类纯文本模型补上「眼睛和耳朵」的完整视觉/听觉能力 —— 读图、OCR 取字、物体检测定位、视频理解、语音转写、多说话人分离、音乐分析、文档/PDF 可视化、截图直读、图像分割。双通道:默认走 MCP 工具(通义千问),也可用 vision.py 接任意 OpenAI 兼容供应商。.

Yts1919/dsh-vision-complete · 112 tokens

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

image-generator

Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.

lessweb/deepcode-cli · 62 tokens

weibo-poster

微博内容创作 - 140字优化、话题热搜、@提及策略、配图描述、发布时机.

dongsheng123132/u-claw · 32 tokens

xiaohongshu-writer

小红书笔记写作助手 - 标题优化、emoji策略、话题标签、封面文案、笔记结构.

dongsheng123132/u-claw · 35 tokens

excel-helper

Excel 表格助手 - 公式编写、数据透视表、图表可视化、宏自动化、数据清洗.

dongsheng123132/u-claw · 31 tokens