A set of tools for using the Internet Archive’s Wayback Machine, which stores older copies of web pages. It can check archives, compare page versions, save new captures, and search Internet Archive records.

Use it to find the nearest saved page, inspect a URL’s change timeline, detect link rot, capture a page, search the archive, and read item metadata.

It helps when a link is broken, a page has changed, or you need evidence of what a website contained at a particular time.

wayback — 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 wayback

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/wayback/github.svg)](https://agentmods.dev/skills/mikkoparkkola/nab/wayback)

Your own site

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

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,435 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

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 →

high Privilege Escalation · line 113
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.

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	$0.00094	$0.01435
Opus 5	$0.00047	$0.00718
Sonnet 5	$0.00019	$0.00287
Haiku 4.5	$0.00009	$0.00144

Measured 9d ago against content hash 04a0650e8bcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wayback 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/cdx_paper_diff.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.

plugin/skills/wayback/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wayback Machine Skill

Five tools wrapped via mcp-gateway. All anonymous; wayback_save optionally uses OREILLY_API_KEY-style auth via IA_ACCESS_KEY + IA_SECRET_KEY for the higher rate ceiling.

Decision tree

Q: "Is this URL archived?"            → fulcrum:wayback_availability
Q: "Show me snapshots of X over time" → fulcrum:wayback_cdx
Q: "Has this page changed?"           → fulcrum:wayback_cdx (collapse=digest)
Q: "Capture this URL now"             → fulcrum:wayback_save
Q: "What new items appeared?"         → fulcrum:internet_archive_changes
Q: "Pull the metadata of an item"     → fulcrum:internet_archive_metadata
Q: "Search the IA catalog"            → fulcrum:internet_archive_search
Q: "Upload/download with `ia` CLI"    → use sibling skill `ia`

High-leverage workflows

1. Patent-grade evidence locking (MIK-3344 line)

# Lock in adversarial-resistant proof at triage time
gateway_execute("fulcrum:wayback_save", {
  "url": "<source>",
  "capture_screenshot": "1",
  "if_not_archived_within": "1d"  # idempotent
})
# job returns; then 30 sec later:
gateway_execute("fulcrum:wayback_availability", {
  "url": "<source>",
  "timestamp": "<job-time>"
})
# returns court-admissible Wayback URL with timestamp

2. Paper-revision detection across prior-art portfolio (MIK-3355)

# Weekly diff for each tracked arxiv paper:
rows = gateway_execute("fulcrum:wayback_cdx", {
  "url": "arxiv.org/abs/<id>",
  "collapse": "digest",       # one row per unique content hash
  "from": "<last-check-ts>",
  "output": "json"
})
# different digest = paper was revised; alert + re-read body

Operational contract:

Keep the tracked paper list in ~/.claude/data/portfolio/cdx_paper_diff_config.json.
Run ~/.claude/data/portfolio/cdx_paper_diff.py weekly. The script calls fulcrum:wayback_cdx via the local mcp-gateway CLI using collapse: "digest" and from: <last-check-ts> for each configured arXiv ID.
Persist state in ~/.claude/data/portfolio/cdx_paper_diff_state.json. First run is a baseline and must not alert on newly observed digests.
On later runs, a digest change emits a Linear comment on the configured patent/prior-art ticket. If a paper is intentionally untracked, enable linear.create_untracked in the config to file a new MIK ticket.
Schedule manifest: ~/.claude/data/portfolio/cdx_paper_diff_schedule.json uses cron expression 0 9 * * 1 (Mondays 09:00 UTC, Mondays 12:00 Helsinki during UTC+03) for remote-agent scheduling.
If failed_or_empty / papers exceeds max_error_rate (default 5%), treat the run as needing fallback to slower per-paper wayback_availability probes before trusting the weekly digest gate.

Read the full file on GitHub · 135 lines

Files

What ships with it

1 file 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.

scripts/cdx_paper_diff.py 16 KB runs code

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 · 135 lines · 94 tokens per session scan A 04a0650e8bcc

Subscribe to this mod's changes

wayback is a skill published in the GitHub repository MikkoParkkola/nab (12 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,435 once invoked, about $0.0005 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.

Rust Security 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

wayback