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 AI-Riksarkivet/ra-mcp --skill archive-researchgit clone --depth 1 https://github.com/AI-Riksarkivet/ra-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/ai-riksarkivet/ra-mcp/archive-research)<a href="https://agentmods.dev/skills/ai-riksarkivet/ra-mcp/archive-research"><img src="https://agentmods.dev/badge/skills/ai-riksarkivet/ra-mcp/archive-research/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/ai-riksarkivet/ra-mcp/archive-research"><img src="https://agentmods.dev/badge/skills/ai-riksarkivet/ra-mcp/archive-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.01360 |
| Opus 5 | $0.00043 | $0.00680 |
| Sonnet 5 | $0.00017 | $0.00272 |
| Haiku 4.5 | $0.00009 | $0.00136 |
Grade A, and why
archive-research 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 11d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archive Research Guide
Research integrity, methodology, and workflows for historical research using the Riksarkivet MCP tools.
Research Integrity Rules
This is an academic research tool. Accuracy and proper sourcing are paramount.
- Never fabricate data. Never guess or hallucinate reference codes, page numbers, dates, names, or any archival data. Every claim must come directly from tool results.
- Always cite precisely. Cite the exact reference code and page number when presenting information from a document (e.g. "SE/RA/420422/01/A I a 1/288, page 66").
- Only use returned links. Only use links explicitly returned by the tools (bildvisaren, ALTO XML, NAD links, IIIF URLs). Never construct or guess URLs — not even by combining a base URL with a reference code.
- Distinguish source from interpretation. Clearly separate what the document says (quote or close paraphrase with quotation marks) from your own interpretation or translation.
- Flag uncertainty. If a transcription is unclear, incomplete, or ambiguous, say so explicitly. Do not silently fill in gaps with plausible-sounding text. Remember: all transcriptions are AI-generated (HTR/OCR) and contain recognition errors — misread characters, merged words, and garbled passages are common.
- Mark translations. When translating old Swedish, mark it as a translation and note when the meaning is uncertain.
- Admit gaps. If you cannot find information the user is looking for, say so. Do not construct an answer from partial or unrelated results.
Understanding the Research Goal
Before making your first search, ensure you understand what the user is researching. If their intent is vague or unclear, ask clarifying questions:
- What time period are they interested in?
- What type of documents are they looking for (court records, church records, military, estates)?
- Are they researching a specific person, family, place, or event?
- What do they already know that could help narrow the search?
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.
- 11d ago First seen · 137 lines · 85 tokens per session scan A 8f9bb89b5769
archive-research is a skill published in the GitHub repository AI-Riksarkivet/ra-mcp (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 85 tokens to every session and 1,360 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 2026-08-30.
Other skills, from other repositories
daily-briefing
Start your day with a prioritized CRM briefing — works for any monday CRM setup: pipeline, contacts, accounts, leads, or no board at all. Use when someone says 'morning briefing', 'daily brief', 'what's on my plate today', 'catch me up on my deals', 'what needs attention', 'what needs my attention', 'anything urgent…
workspace-builder
Build a CRM workspace from scratch — describe your business and get boards, columns, and pipeline stages created in monday. Use when someone says "set up my CRM", "build me a CRM", "create CRM boards for me", "I need a new sales pipeline", "help me get started in monday", "I don't know how to set up my pipeline", or…
data-cleanup
Check your CRM board's health and clean up messy data — run a scored health check (missing fields, stalled deals, abandoned columns, automation gaps) as a report, or fix data in bulk (phone formats, missing emails, country codes, unowned deals, stale dates). Use when someone says "clean my CRM", "fix my data"…
meeting-to-deal
Turn meeting transcripts into deal updates — key points, commitments, and next steps posted to matching CRM deals automatically. Auto-creates contacts for new attendees. Use when someone says "log my meetings to deals", "update CRM from calls", "what did I commit to in meetings", "sync notetaker", "log this meeting"…
forecast
Build a forecast dashboard in monday — committed, best-case, and pipeline views by close month, rendered as real dashboard widgets. Use when someone says "build me a forecast", "show me Q2 pipeline", "Salesforce-style forecast", "forecast dashboard", "commit vs best-case", "what's our number this quarter", "how are we…
run-sequence
Manage CRM sequences end-to-end — list, create, enroll contacts, activate/deactivate, duplicate, and track performance. Use when someone says "what sequences do I have", "create a welcome sequence", "enroll this contact in a sequence", "add these leads to my nurture sequence", "deactivate the cold outreach sequence"…