A command-line skill for Internet Archive, a website that stores books, music, films, software, datasets, and other preserved files. It supports searching the archive and working with grouped collections called items.

Use it to search Internet Archive, download items or files, upload files, inspect item metadata, and work with archive.org collections through the ia command-line tool.

It gives a coding agent a documented way to retrieve or upload archived material while accounting for item structure, file limits, metadata, and permanent URLs.

ia — Skill for Claude Code by MikkoParkkola

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 MikkoParkkola/nab --skill ia

Clone the repo

git clone --depth 1 https://github.com/MikkoParkkola/nab

Made for: Claude Code.

Or install nab, the plugin that ships this one along with the rest of its 6 skills, 1 command, 1 hook, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mikkoparkkola/nab/ia/github.svg)](https://agentmods.dev/skills/mikkoparkkola/nab/ia)

Your own site

<a href="https://agentmods.dev/skills/mikkoparkkola/nab/ia"><img src="https://agentmods.dev/badge/skills/mikkoparkkola/nab/ia/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mikkoparkkola/nab/ia"><img src="https://agentmods.dev/badge/skills/mikkoparkkola/nab/ia.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,685 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 577
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.06685
Opus 5	$0.00022	$0.03342
Sonnet 5	$0.00009	$0.01337
Haiku 4.5	$0.00004	$0.00668

Measured 9d ago against content hash 63d343d51dfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ia scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**All requests to the Internet Archive must include a proper User-Agent string** that clearly identifies the source of the request. This applies to every request made via any tool - the `ia` CLI, Python library, direct A

plugin/skills/ia/SKILL.md · 866 lines

How it starts

The opening of the file, as written. The whole thing — 866 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Internet Archive CLI Skill

This skill enables interaction with the Internet Archive (archive.org) using the ia command-line tool from the internetarchive Python package.

Items

An item is the fundamental unit on archive.org - a logical grouping of related files sharing common metadata. An item can be a book, a song, an album, a dataset, a movie, an image or set of images, etc. Each item has a unique identifier across the entire archive.

Every item contains:

Original uploaded files
Derivative files (automatically generated by archive.org)
<identifier>_meta.xml - item-level metadata
<identifier>_files.xml - file-level metadata

Items must belong to a collection.

Item Limits

Constraint	Recommended	Hard Limit
Item total size	Under 100GB	~1TB
Files per item	Under 10,000	250,000 (performance degrades >10,000)
Single file size	Under 50GB	500-700GB
Daily upload	Under 1,000 files	5,000 files (zips count as 1)

Permanent URL patterns:

Details page: https://archive.org/details/<identifier>
Download directory: https://archive.org/download/<identifier>
Specific file: https://archive.org/download/<identifier>/<filename>
Item history: https://archive.org/history/<identifier>

Warning: Never link to server-specific URLs like ia802304.us.archive.org - these break when items migrate between servers. Always use the canonical archive.org URLs above.

For more details, see: https://archive.org/developers/items.html

Derivatives

When you upload files to the Internet Archive, the system automatically generates derivative files - converted versions in different formats and resolutions. For example:

Video: Transcoded to h.264, Ogg, and various bitrates
Audio: Converted to MP3 (multiple bitrates), Ogg Vorbis, FLAC
Text/Books: OCR processing, searchable PDFs, EPUB, DjVu
Images: Thumbnails, JPEG 2000, different resolutions

Derivatives make content accessible across different devices and bandwidths. You can identify derivatives in ia list output - they have an original field pointing to their source file.

Read the full file on GitHub · 866 lines

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.

9d ago First seen · 866 lines · 43 tokens per session scan A 63d343d51dfb

Subscribe to this mod's changes

ia is a skill published in the GitHub repository MikkoParkkola/nab (12 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 6,685 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Research Rust Writing and docs anti-bot cli cookies http3 passkeys

cw-gates

Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.

Hmbown/Codewhale · 48 tokens

contributor-onboarding

Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.

Hmbown/CodeWhale · 57 tokens

ia