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 skills add chaterm/terminal-skills --skill tar-compressiongit clone --depth 1 https://github.com/chaterm/terminal-skillsWrote 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/chaterm/terminal-skills/tar-compression)<a href="https://agentmods.dev/skills/chaterm/terminal-skills/tar-compression"><img src="https://agentmods.dev/badge/skills/chaterm/terminal-skills/tar-compression/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chaterm/terminal-skills/tar-compression"><img src="https://agentmods.dev/badge/skills/chaterm/terminal-skills/tar-compression.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00009 | $0.01543 |
| Opus 5 | $0.00005 | $0.00772 |
| Sonnet 5 | $0.00002 | $0.00309 |
| Haiku 4.5 | $0.00001 | $0.00154 |
Grade A, and why
tar-compression 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 9d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
归档与压缩
概述
tar/gzip/xz 归档压缩、分卷备份技能。
tar 基础
创建归档
# 创建 tar 归档
tar -cvf archive.tar /path/to/dir
# 创建并 gzip 压缩
tar -czvf archive.tar.gz /path/to/dir
# 创建并 bzip2 压缩
tar -cjvf archive.tar.bz2 /path/to/dir
# 创建并 xz 压缩
tar -cJvf archive.tar.xz /path/to/dir
# 多个目录/文件
tar -czvf archive.tar.gz dir1 dir2 file1.txt
解压归档
# 解压 tar
tar -xvf archive.tar
# 解压 gzip
tar -xzvf archive.tar.gz
# 解压 bzip2
tar -xjvf archive.tar.bz2
# 解压 xz
tar -xJvf archive.tar.xz
# 解压到指定目录
tar -xzvf archive.tar.gz -C /target/dir
查看内容
# 列出内容
tar -tvf archive.tar
tar -tzvf archive.tar.gz
# 搜索文件
tar -tzvf archive.tar.gz | grep "filename"
常用选项
# 排除文件/目录
tar -czvf archive.tar.gz --exclude='*.log' --exclude='cache' /path
# 从文件读取排除列表
tar -czvf archive.tar.gz --exclude-from=exclude.txt /path
# 保留权限
tar -czvf archive.tar.gz --preserve-permissions /path
# 增量备份
tar -czvf archive.tar.gz --newer='2024-01-01' /path
压缩工具
gzip
# 压缩
gzip file.txt # 生成 file.txt.gz,删除原文件
gzip -k file.txt # 保留原文件
gzip -9 file.txt # 最高压缩率
# 解压
gunzip file.txt.gz
gzip -d file.txt.gz
# 查看压缩文件
zcat file.txt.gz
zless file.txt.gz
zgrep "pattern" file.txt.gz
bzip2
# 压缩
bzip2 file.txt
bzip2 -k file.txt # 保留原文件
bzip2 -9 file.txt # 最高压缩率
# 解压
bunzip2 file.txt.bz2
bzip2 -d file.txt.bz2
# 查看
bzcat file.txt.bz2
xz
# 压缩
xz file.txt
xz -k file.txt # 保留原文件
xz -9 file.txt # 最高压缩率
xz -T 4 file.txt # 多线程
# 解压
unxz file.txt.xz
xz -d file.txt.xz
# 查看
xzcat file.txt.xz
zstd
# 压缩
zstd file.txt
zstd -19 file.txt # 最高压缩率
zstd -T0 file.txt # 自动多线程
# 解压
unzstd file.txt.zst
zstd -d file.txt.zst
分卷备份
split 分割
# 按大小分割
split -b 100M archive.tar.gz archive.tar.gz.part_
# 按行分割
split -l 10000 largefile.txt part_
# 合并
cat archive.tar.gz.part_* > archive.tar.gz
tar 分卷
# 创建分卷
tar -czvf - /path/to/dir | split -b 100M - backup.tar.gz.part_
# 解压分卷
cat backup.tar.gz.part_* | tar -xzvf -
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.
- 9d ago First seen · 246 lines · 9 tokens per session scan A a8f19069141a
tar-compression is a skill published in the GitHub repository chaterm/terminal-skills (58 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 9 tokens to every session and 1,543 once invoked, about $0.0000 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
c-files
Sync files to Google Drive, S3, Dropbox, OneDrive, and 70+ cloud providers using rclone.
skillci-guardrails
Use this skill whenever you create, edit, or review a Claude Skill — any SKILL.md file, or the eval cases/config next to one. Most SKILL.md files today are written or edited by an agent, not typed by hand, so this closes the loop by having the agent that just wrote the skill also author it defensively and verify it…
example-skill
Writes a single changelog entry summarizing a code change, given a short description of what changed.
clean-skill
A skill with no lint issues, used as a starting point for the lint-on-type test.
skill-with-referenced-issue
Has a clean SKILL.md but an unsafe referenced script.
council
Run one request through several skills in parallel, isolated subagents, then merge their answers or judge the single best one. Use when the user invokes /council (or /council manage), or uses clear multi-skill-comparison language like "try this with a few different skills", "compare how different skills answer this"…