Borrowing it
Nothing to install: this file belongs to nestordemeure/gallica-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/gallica-mcp/main/.claude/skills/gallica-search/SKILL.mdgit clone --depth 1 https://github.com/nestordemeure/gallica-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/gallica-mcp/gallica-search)<a href="https://agentmods.dev/skills/nestordemeure/gallica-mcp/gallica-search"><img src="https://agentmods.dev/badge/skills/nestordemeure/gallica-mcp/gallica-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/gallica-mcp/gallica-search"><img src="https://agentmods.dev/badge/skills/nestordemeure/gallica-mcp/gallica-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 | $0.00052 | $0.03900 |
| Opus 5.5 | $0.00021 | $0.01560 |
| Sonnet 5.5 | $0.00010 | $0.00780 |
| Haiku 4.5 | $0.00005 | $0.00390 |
Grade A, and why
gallica-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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gallica
The digital library of the BnF: French newspapers, periodicals, books and manuscripts. It also holds some English-language titles, such as the Paris edition of the New York Herald. Use it for European press reports about performers who travelled in Continental Europe.
Commands
gallica search "<query>" [--pages N|N-M|all] [--sort ORDER] [filters] [--json]
gallica snippets <ark> "<query>" # where the query appears inside one document
gallica get <ark> [--pages 30-35] # download OCR text, prints path to the cached file
Note that --pages has a different meaning on each command. On search it means the result pages. On get it means the document pages.
The filters for search are --creator NAME (repeatable), --type TYPE (repeatable, from monographie, périodique, fascicule, manuscrit, image, carte, partition), --from-year, --to-year, --language CODE (ISO 639-2: fre, eng, ger…), --title TEXT, --subject HEADING, --publisher NAME, --library NAME, --min-ocr-quality SCORE, --include-restricted and --fuzzy.
--sort takes relevance (default), date_asc or date_desc.
A search gives no snippets. This is the important difference in the procedure. search gives you documents. Then snippets tells you if a document has value. Only then does get download it. If you go directly from search to get, you spend a large download on documents that hold one brief mention.
snippets marks the matched terms with {braces} and gives a page identifier such as PAG_30 for each occurrence. Its snippets hold one or two sentences of real context, not a few words. Thus they are frequently enough to judge a document and to quote it in a report with no download.
These page identifiers go directly into get. Gallica sends the OCR one page for each request, so get takes a page range, and --pages accepts the PAG_30 form exactly:
gallica snippets ark:/12148/bd6t5841739g "prestidigitateur" # → occurrences on PAG_3, PAG_4
gallica get ark:/12148/bd6t5841739g --pages PAG_3-PAG_4 # → two requests, not sixteen
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 · 132 lines · 52 tokens per session scan A 051cf78feb39
gallica-search is a skill published in the GitHub repository nestordemeure/gallica-mcp (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 3,900 once invoked, about $0.0002 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.
gallica-search compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gallica-searchnestordemeure/gallica-mcp | Skill | 1 | 3mo ago | Apache-2.0 | A | 52 | Claude Code |
| opik-diagnosecomet-ml/opik-mcp | Skill | 225 | 9d ago | Apache-2.0 | A | 187 | Claude Code |
| ue-mcp-epic-routingdb-lyon/ue-mcp | Skill | 476 | yesterday | MIT | A | 81 | Claude Code, Codex |
| qa-knowledgegriddynamics/rosetta | Skill | 370 | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| apitapn1byn1kt/apitap | Skill | 131 | 17d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| frontmcp-setupagentfront/frontmcp | Skill | 148 | yesterday | Apache-2.0 | A | 176 | Claude Code, Codex |
| x-use-reviewihuzaifashoukat/x-use | Skill | 181 | 4d ago | MIT | A | 56 | Claude Code |