Borrowing it
Nothing to install: this file belongs to nestordemeure/impresso-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/impresso-mcp/main/.claude/skills/impresso-search/SKILL.mdgit clone --depth 1 https://github.com/nestordemeure/impresso-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/impresso-mcp/impresso-search)<a href="https://agentmods.dev/skills/nestordemeure/impresso-mcp/impresso-search"><img src="https://agentmods.dev/badge/skills/nestordemeure/impresso-mcp/impresso-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/impresso-mcp/impresso-search"><img src="https://agentmods.dev/badge/skills/nestordemeure/impresso-mcp/impresso-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 | $0.03694 |
| Opus 5.5 | $0.00030 | $0.01478 |
| Sonnet 5.5 | $0.00015 | $0.00739 |
| Haiku 4.5 | $0.00007 | $0.00369 |
Grade A, and why
impresso-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 2mo 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
impresso (Swiss and Luxembourgish press)
The digitised press of Switzerland and Luxembourg, with a full-text search at the level of the individual article. The period is 1738 to 2018. The languages are German, French, Luxembourgish and Italian. The corpus holds 141 publications.
This source has four properties that the other sources do not have together:
- A search gives one article, not one issue and not one page. Each result holds its date, its publication, its page number, its length in words and its keyword-in-context extracts.
- The full transcript comes to you, also for material that is still in copyright. A test read the full text of an article from 1974. The rights status does not stop the download.
- The query language is the most powerful in this toolkit. It has a control of the precision, a regular expression filter, a named-entity filter, and a filter for advertisements.
- The pagination has no limit. A test reached position 499,900 of a result set of 601,658, with no error.
When to use this source
Use impresso for these subjects:
- the German-language press of Switzerland, above all the Neue Zürcher Zeitung (112,672 issues, 1780 to 1950)
- the press of Luxembourg, which no other source in this toolkit holds
- each question that needs the complete text of an article, and not only an extract
- a subject after 1900, where the other European sources stop or give the metadata only
Read this before you use impresso and Gallica together
impresso holds French national newspapers as well as Swiss and Luxembourgish ones. The list includes the Journal des débats politiques et littéraires (33,610 issues), Le Gaulois (22,340 issues) and Le Petit Parisien (20,282 issues).
Gallica holds these same three titles. Thus a search of both sources finds the same material two times. Do not add the totals of the two sources. When a result comes from one of these French titles, say which source you used, and do not count it again.
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.
- 2mo ago First seen · 245 lines · 75 tokens per session scan A 505ffa9cf517
impresso-search is a skill published in the GitHub repository nestordemeure/impresso-mcp (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 3,694 once invoked, about $0.0003 per session on Opus 5.5. 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.
impresso-search compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| impresso-searchnestordemeure/impresso-mcp | Skill | 0 | 3mo ago | Apache-2.0 | A | 75 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |