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.
npx skills add nestordemeure/loc-mcp --skill loc-searchgit clone --depth 1 https://github.com/nestordemeure/loc-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/loc-mcp/loc-search)<a href="https://agentmods.dev/skills/nestordemeure/loc-mcp/loc-search"><img src="https://agentmods.dev/badge/skills/nestordemeure/loc-mcp/loc-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/loc-mcp/loc-search"><img src="https://agentmods.dev/badge/skills/nestordemeure/loc-mcp/loc-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 | $0.00074 | $0.08132 |
| Opus 5 | $0.00037 | $0.04066 |
| Sonnet 5 | $0.00015 | $0.01626 |
| Haiku 4.5 | $0.00007 | $0.00813 |
Grade A, and why
loc-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 12d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Library of Congress
One API with no key over each item that the Library of Congress digitised and transcribed: newspapers from 1736 to 1963, digitised books, and manuscript collections. Each item has a full-text index, and each item resolves to the individual page.
Use it for the American part of a career — the tour circuit, local notices, and articles that explain methods. It is the counterpart to Gallica and ANNO. Two properties make it different:
- It is not only newspapers. The books and the manuscripts are in the same index, and they search in the same way. Thus the conjuring literature and the personal papers come back together with the press. A search of everything is the default, and
--collectionis how you make the search narrow. - It is not only English. The newspaper corpus holds many languages. The American immigrant press published in more languages than most national archives hold.
Coverage by language
The pages in the newspaper collection, from its own language facet:
| english 22,499,675 | german 619,712 | spanish 453,914 | polish 169,005 |
| french 135,671 | yiddish 132,713 | italian 88,547 | czech 58,960 |
| norwegian 49,635 | serbian 46,789 |
Each language searches in the same way. The community that came to a performance in the United States wrote about the performer, so the Spanish, Polish and Yiddish press are not a small detail. Frequently they hold a notice that the English papers did not print.
The shape of each decade is very different for each language, and it decides if a subset is worth a search. Each column sums to the total for that language exactly, so these are counts and not estimates:
| Decade | german | spanish | polish | yiddish | italian |
|---|---|---|---|---|---|
| 1880s | 22,933 | 1,642 | 1 | — | |
| 1890s | 103,779 | 44,278 | 22,010 | 296 | 3,974 |
| 1900s | 128,127 | 63,073 | 39,083 | 0 | 24,033 |
| 1910s | 177,394 | 66,021 | 70,108 | 24,719 | 34,400 |
| 1920s | 24,075 | 70,765 | 31,847 | 24,178 | 6,705 |
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.
- 12d ago First seen · 324 lines · 74 tokens per session scan A fa44ac603d08
loc-search is a skill published in the GitHub repository nestordemeure/loc-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 8,132 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 2026-08-31.
Other skills, from other repositories
frontmcp-development
Use when building any FrontMCP server component other than a tool (for tools, use create-tool). Covers @Resource static resources and parameterized URI templates; @Prompt reusable prompts (RAG, multi-turn); @Provider singleton dependency-injection providers (database pools, API clients); @Agent autonomous LLM agents…
pipefy-ai-agents
Use this skill when the user wants to create, read, update, delete, or troubleshoot AI agents (conversational agents with behaviors). Covers 7 MCP tools including pre-flight validation, plus pipe-scoped knowledge bases (list, plain text/document/data lookup CRUD, access probe) attached via dataSourceIds. For…
pipefy-automations
Use this skill when the user wants to create, read, update, or delete traditional automations (if/then rules) or AI automations (prompt-driven). Covers 16 MCP tools. For AI agents (conversational), see skills/ai-agents/.
html-portal-generator
Convert a codebase into a self-contained HTML portal app for ingestion into AI application systems. Produces a single deployable HTML file with embedded CSS, JS, and data.
pipefy-ipaas
Use when the user wants to build, test, publish, or manage iPaaS (Advanced Automations) flows: multi-step integrations with external apps (Slack, Gmail, Google Sheets), incoming webhooks, schedules, routers, code steps, or iPaaS data tables. MCP-only, driven through 4 meta-tools over a per-pipe catalog discovered at…
pipefy-portal-setup
Use this skill when the user wants to list, create, or configure Pipefy portals (main hub, pages, page elements, sub-portals, publish/unpublish). Covers 20 MCP tools on Interfaces + internalapi. Not for pipes/cards.