Borrowing it
Nothing to install: this file belongs to nestordemeure/lantern-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nestordemeure/lantern-mcp/main/.claude/skills/lantern-search/SKILL.mdgit clone --depth 1 https://github.com/nestordemeure/lantern-mcpWrote 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/nestordemeure/lantern-mcp/lantern-search)<a href="https://agentmods.dev/skills/nestordemeure/lantern-mcp/lantern-search"><img src="https://agentmods.dev/badge/skills/nestordemeure/lantern-mcp/lantern-search/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/nestordemeure/lantern-mcp/lantern-search"><img src="https://agentmods.dev/badge/skills/nestordemeure/lantern-mcp/lantern-search.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 | $0.00075 | $0.04028 |
| Opus 5 | $0.00037 | $0.02014 |
| Sonnet 5 | $0.00015 | $0.00806 |
| Haiku 4.5 | $0.00007 | $0.00403 |
Grade A, and why
lantern-search 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 10d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lantern (Media History Digital Library)
The digitised entertainment trade press, with a full-text index and no key: Variety, Billboard, the New York Clipper, Motion Picture Herald, Boxoffice, The Film Daily, the studio year books and the fan magazines. The period is approximately 1900 to 1960, and the Clipper goes back into the 19th century.
Do not search this archive in the way that you search a newspaper archive. It is not one. Each other source in this toolkit gives you the general press: what the industry told the public. Lantern gives you the industry that writes about itself — who had a booking and where, for what money, who died, whose act a competitor stole, and which theatre had no show that week. A minor performer who took whatever bookings came usually has no other continuous record.
Use it for these subjects:
- routes and bookings
- salaries
- descriptions of acts by people who saw the act on the same night
- obituaries
- disputes about billing
- the terms that the trade used for what an act was
Lantern and Internet Archive hold almost the same material — read this before you use both
The scans that Lantern indexes are Internet Archive items, in the mediahistory collection, and the archives client searches their full text correctly. These are not two archives. They are two indexes of one archive. On "mind reader" they find the same material: archives --collection mediahistory reports 1,142 documents, and Lantern reports 1,783 pages across approximately 1,090 volumes.
Thus do not search both sources and add the totals. The same page found two times is one page. If a report gives a number from each source, that report counts the same material two times.
Lantern has value for two reasons only:
- It resolves a result to a page, and
archivescannot. For this material, the usual solution of a download and a local grep does not give the position either.archives get variety04-1906-10gives 881 KB of text that holds the phrase and no page boundaries of any type. Thus you can find the passage but you cannot cite it. Lantern gives the leaf number in the search response, with no additional cost. - Its
--collectioncategories separate the stage from film —Theatre and VaudevilleandEarly Cinema. Internet Archive has no equivalent, and this is the difference between 1,783 results and the 546 results that concern a stage act.
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.
- 10d ago First seen · 199 lines · 75 tokens per session scan A ada7791be591
lantern-search is a skill published in the GitHub repository nestordemeure/lantern-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 4,028 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 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…