zlib-download

zlib-download is a skill for Claude Code from psylch/zlib-download-skill. It costs 79 tokens per session (1,795 once invoked), scanned A, original, MIT.

A set of book-search and download tools that uses Z-Library and Anna's Archive as sources. It combines these sources behind one command-line interface.

In plain words
What is it for?
It is for finding and downloading books, ebooks, and papers, after installing the required dependencies and configuring the needed account details or API key.
Why use it?
It avoids searching each source separately and can use different sources or mirrors when available.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the zlib-download plugin — 1 skill shipped together

Good fit It is for finding and downloading books, ebooks, and papers, after installing the required dependencies and configuring the needed account details or API key.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/psylch/zlib-download-skill/zlib-download
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.

Any agent
npx skills add psylch/zlib-download-skill --skill zlib-download
Clone the repo
git clone --depth 1 https://github.com/psylch/zlib-download-skill

Made for: Claude Code.

Or install zlib-download, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for zlib-download

README.md
[![agentmods](https://agentmods.dev/badge/skills/psylch/zlib-download-skill/zlib-download/github.svg)](https://agentmods.dev/skills/psylch/zlib-download-skill/zlib-download)
Your own site
<a href="https://agentmods.dev/skills/psylch/zlib-download-skill/zlib-download"><img src="https://agentmods.dev/badge/skills/psylch/zlib-download-skill/zlib-download/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.

agentmods 80×15 button for zlib-download

Your own site · 80×15
<a href="https://agentmods.dev/skills/psylch/zlib-download-skill/zlib-download"><img src="https://agentmods.dev/badge/skills/psylch/zlib-download-skill/zlib-download.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,795 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00079 $0.01795
Opus 5 $0.00039 $0.00898
Sonnet 5 $0.00016 $0.00359
Haiku 4.5 $0.00008 $0.00179

Measured 11d ago against content hash 33e99df7c762, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

zlib-download 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 11d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/book.py, scripts/setup.sh, scripts/Zlibrary.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/zlib-download/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Book Tools

Search and download books from multiple sources through a unified CLI.

Backends

Backend Source Auth Required Best For
zlib Z-Library (EAPI) Email + Password Largest catalog, direct download
annas Anna's Archive API Key (donation) Aggregated sources, multiple mirrors

First-Time Setup

On first invocation, run the setup check and guide the user through configuration interactively.

Step 1: Check Dependencies

bash ${SKILL_PATH}/scripts/setup.sh check

Output is key=value pairs. Check each:

Key OK Missing Action
PYTHON ok Python 3 not found — user must install it
REQUESTS ok Run bash ${SKILL_PATH}/scripts/setup.sh install-deps
ANNAS_BINARY ok Run bash ${SKILL_PATH}/scripts/setup.sh install-annas (optional)

Step 2: Configure Credentials

Credentials are stored in ~/.claude/book-tools/.env. Create the file from the skill's bundled template:

mkdir -p ~/.claude/book-tools
cp ${SKILL_PATH}/scripts/.env.example ~/.claude/book-tools/.env

The .env file looks like this:

# Z-Library credentials
[email protected]
ZLIB_PASSWORD=your_password_here

# Anna's Archive (optional, requires donation for API key)
# ANNAS_SECRET_KEY=your_api_key_here

IMPORTANT: Do NOT ask the user for credentials directly in chat. Instead:

  1. Create the .env file (or .env.example template)
  2. Tell the user to edit ~/.claude/book-tools/.env with their credentials
  3. Wait for the user to confirm they've filled it in
  4. Then proceed with search

Alternatively, credentials can be set via CLI (less recommended — visible in shell history):

python3 ${SKILL_PATH}/scripts/book.py config set --zlib-email "[email protected]" --zlib-password "password"

Step 3: Verify

python3 ${SKILL_PATH}/scripts/book.py setup

Expected output when Z-Library is configured:

{
  "zlib": { "requests_installed": true, "configured": true },
  "annas": { "binary_found": true, "api_key_configured": false }
}

Read the full file on GitHub · 217 lines

Files

What ships with it

5 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.

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. 11d ago First seen · 217 lines · 79 tokens per session scan A 33e99df7c762

Subscribe to this mod's changes

zlib-download is a skill published in the GitHub repository psylch/zlib-download-skill (10 stars, last pushed 6mo ago), licensed MIT. It adds 79 tokens to every session and 1,795 once invoked, about $0.0004 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.