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 johnhringiv/notes-mcp --skill resource-ingestiongit clone --depth 1 https://github.com/johnhringiv/notes-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/johnhringiv/notes-mcp/resource-ingestion)<a href="https://agentmods.dev/skills/johnhringiv/notes-mcp/resource-ingestion"><img src="https://agentmods.dev/badge/skills/johnhringiv/notes-mcp/resource-ingestion/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/johnhringiv/notes-mcp/resource-ingestion"><img src="https://agentmods.dev/badge/skills/johnhringiv/notes-mcp/resource-ingestion.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 | $0.00063 | $0.00722 |
| Opus 5 | $0.00032 | $0.00361 |
| Sonnet 5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
resource-ingestion 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 8d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Importing documents into the notes resources library
Resources are reference documents, distinct from notes: imported rather than
authored, read in ranges, never edited in place. They live under
resources/<topic>/<slug>.md and are searchable via search_notes (hits
carry a resource_id).
Decide fidelity first
- verbatim — the exact text matters (specs, papers the user will quote, standards). Only feasible if you can reproduce the text faithfully.
- digest — a structured distillation: summary, key sections quoted exactly, the rest condensed. Use when the document is long, when only parts matter, or when a faithful full transfer is not feasible.
When in doubt, ask the user which they want. Never silently abridge a
transfer that claims fidelity: verbatim — if the document is too long to
transfer faithfully, say so and offer a digest or the desktop path.
Size gates (be honest about transfer limits)
- < ~1,500 lines: full verbatim transfer is realistic. Proceed.
- ~1,500–5,000 lines: verbatim only if the user confirms; expect many append calls. Digest usually serves better.
- > ~5,000 lines (books): do not attempt through chat. Tell the user to
convert on their desktop and commit directly to
resources/in the notes repo — the server picks it up on its next pull.
Procedure
-
Obtain the text (fetch the URL yourself, or read the user's upload).
-
Choose an id:
<topic>/<slug>.md(e.g.maeve/austral-spec.md). Checklist_resourcesfor collisions —add_resourcewithout append REPLACES an existing resource. -
First
add_resourcecall: frontmatter + the opening chunk:--- title: The Austral Specification source: https://austral-lang.org/spec/spec.html retrieved: 2026-07-06 fidelity: verbatim --- (first ~150 lines of content) -
Continue with
add_resource(..., append=true)in chunks of ~100–200 lines. Preserve the original text exactly for verbatim imports — headings, code blocks, everything. -
Verify: the final response's
total_linesshould match your expectation from the source. Spot-check withread_resourceat a couple of offsets (start, middle, end). If content is missing, say so and repair or restart the transfer. -
Report to the user: id, fidelity, size, source, and one line on how to find 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.
- 8d ago First seen · 69 lines · 63 tokens per session scan A 6c96b194d043
resource-ingestion is a skill published in the GitHub repository johnhringiv/notes-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 722 once invoked, about $0.0003 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.