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/cn-big-cabbage/github-skill-distiller/fzfnpx skills add CN-big-cabbage/github-skill-distiller --skill fzfgit clone --depth 1 https://github.com/CN-big-cabbage/github-skill-distillerWrote 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/cn-big-cabbage/github-skill-distiller/fzf)<a href="https://agentmods.dev/skills/cn-big-cabbage/github-skill-distiller/fzf"><img src="https://agentmods.dev/badge/skills/cn-big-cabbage/github-skill-distiller/fzf.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 | $0.00017 | $0.01297 |
| Opus 5 | $0.00009 | $0.00648 |
| Sonnet 5 | $0.00003 | $0.00259 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade A, and why
fzf scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fzf 通用命令行模糊查找器
技能概述
本技能帮助用户在命令行中高效使用 fzf 进行模糊查找,适用于以下场景:
- 文件查找: 快速模糊搜索目录树中的文件并打开
- 历史命令: 交互式搜索并重用 Shell 历史命令
- 进程管理: 模糊搜索并终止进程
- Git 工作流: 交互式选择分支、提交、文件差异
- 目录跳转: 快速切换工作目录
- 管道集成: 与任何产生文本输出的命令组合使用
主要特点: 极速模糊匹配、交互式预览、键绑定丰富、与 Shell 深度集成、可嵌入任意脚本
使用流程
AI 助手将引导你完成以下步骤:
- 安装 fzf(如未安装)
- 配置 Shell 集成(键绑定与补全)
- 学习核心用法与快捷键
- 结合常用命令构建高效工作流
关键章节导航
AI 助手能力
当你向 AI 描述查找需求时,AI 会:
- 自动检测系统环境并安装 fzf
- 根据需求生成最优的 fzf 命令组合
- 配置 Shell 集成以启用快捷键
- 构建带预览的交互式文件/内容浏览器
- 生成可复用的 fzf 函数放入 Shell 配置文件
- 集成 fzf 到 Git、Docker、kubectl 等工作流
- 诊断并修复 fzf 配置问题
核心功能
- 极速模糊匹配(基于 Smith-Waterman 算法的改进)
- 支持精确模式(
'word)、前缀匹配(^word)、后缀匹配(word$) - 多选模式(
--multi,Tab 键选择) - 实时预览窗口(
--preview) - 支持 ANSI 颜色代码
- Shell 集成:
CTRL-T(文件)、CTRL-R(历史)、ALT-C(目录) - 自定义按键绑定与动作
- 支持
fd、ripgrep、bat等现代工具联动 - 支持 Vim/Neovim 插件集成
命令速查表
基础用法
# 启动交互式文件选择(当前目录递归)
fzf
# 从标准输入选择
echo -e "foo\nbar\nbaz" | fzf
# 选中后执行命令
vim $(fzf)
# 多选(Tab 选择,Enter 确认)
cat $(fzf --multi)
搜索语法
# 精确匹配(不做模糊)
fzf --query "'exact-word"
# 多词搜索(空格分隔,AND 逻辑)
fzf --query "foo bar"
# OR 逻辑
fzf --query "foo | bar"
# 前缀匹配
fzf --query "^prefix"
# 后缀匹配
fzf --query "suffix$"
# 排除匹配(! 取反)
fzf --query "!unwanted"
预览窗口
# 预览文件内容
fzf --preview 'cat {}'
# 用 bat 高亮预览(推荐)
fzf --preview 'bat --color=always {}'
# 预览窗口位置与大小
fzf --preview 'cat {}' --preview-window=right:50%
# 预览当前行内容
fzf --preview 'echo {}'
Shell 快捷键(安装 Shell 集成后)
# CTRL-T :在命令行插入选中的文件路径
# CTRL-R :搜索并重用历史命令
# ALT-C :cd 进入选中目录
常用参数
# 指定初始查询
fzf --query "initial"
# 反向显示(列表在上,输入框在下)
fzf --reverse
# 显示边框
fzf --border
# 高度模式(不占满全屏)
fzf --height=40%
# 不排序(保持输入顺序)
fzf --no-sort
# 退出码为 0 时清空输出
fzf --exit-0
# 指定分隔符和字段
echo "foo:bar:baz" | fzf --delimiter=: --with-nth=2
安装要求
- macOS / Linux / Windows(WSL 或 Git Bash)
- 可选:
fd(更快的文件查找)、bat(语法高亮预览)、ripgrep(内容搜索)
What ships with it
4 files 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.
- 5d ago First seen · 172 lines · 17 tokens per session scan A 19a2c6d620d2
fzf is a skill published in the GitHub repository CN-big-cabbage/github-skill-distiller (4 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 1,297 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
preparing-for-a-meeting
Use when prepping for any work meeting (1:1, customer call, interview, review) - 60-second-readable brief.
wrapping-up-a-piece
Use when finishing a piece of work - the closing pass that prevents a "done" piece from coming back at you a week later.
cli-framework-cli-commander
Node.js CLI development with Commander.js and @clack/prompts - command structure, interactive prompts, wizard state machines, config hierarchies, exit codes, cancellation handling.
cli-prompts-clack
Beautiful interactive CLI prompts with @clack/prompts and custom prompts with @clack/core.
cli-framework-oclif-ink
Modern CLI development combining oclif's command framework with Ink's React-based terminal rendering.
google-workspace
Gmail, Calendar, Drive, Sheets, Docs via Google API (SA / OAuth).