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 pvliesdonk/markdown-vault-mcp --skill vault-summarizegit clone --depth 1 https://github.com/pvliesdonk/markdown-vault-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/pvliesdonk/markdown-vault-mcp/vault-summarize)<a href="https://agentmods.dev/skills/pvliesdonk/markdown-vault-mcp/vault-summarize"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/vault-summarize/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/pvliesdonk/markdown-vault-mcp/vault-summarize"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/vault-summarize.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 | $0.00055 | $0.00496 |
| Opus 5 | $0.00028 | $0.00248 |
| Sonnet 5 | $0.00011 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
vault-summarize 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 10d 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.
What it actually says
Summarizing vault folders and note sets
When the user asks for a summary, digest, or overview spanning more than one vault note ("summarize my projects folder", "what's in my meeting notes from March"), do not read note after note into the conversation — long vaults overflow the context and the summary degrades. Route the request instead:
1. Check scope
Call get_toc(path=<folder>) first. It returns paths, titles, and headings —
never bodies — so it is always safe. A single short note needs no workflow:
just read it and summarize directly.
2. Prefer the server's one-call route when it is available
If the summarize tool is registered, it produces the whole summary
server-side in one call: summarize(paths=[...], focus=...). Use it unless
the user asks to keep note content away from external providers (the tool
sends note text to its configured backend).
3. Otherwise run the canonical client-side recipe
The server ships the full recipe as its summarize-subtree MCP prompt — that
prompt is the single source of truth for the workflow (plan from the toc,
map in batches of ~8 notes, reduce, deliver with a coverage note). Follow it
with this host's strengths:
- Fan out the map phase as parallel subagents, one per batch, using the
vault-mapperagent this plugin ships — it carries the map-phase instructions and only the vault read tools. Pass each mapper its batch's path list (plus the user's focus, if any). - Subagents cannot spawn subagents: do the planning and the reduce step in the main conversation, keeping only partial summaries — never note bodies — in the retained context.
Do not
- Do not
readmore than one batch of notes in the main conversation. - Do not re-summarize notes a mapper already covered; merge the partials.
- Do not write anything to the vault while summarizing.
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.
- 10d ago First seen · 46 lines · 55 tokens per session scan A 0d8629a4b640
vault-summarize is a skill published in the GitHub repository pvliesdonk/markdown-vault-mcp (32 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 496 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 2026-08-30.
Other skills, from other repositories
mnemonic
Search local indexed markdown knowledge bases. Use when the user asks to find notes, dig up a concept from personal docs, cross-reference ideas across wikis, or answer from indexed local files. Triggers on "look up in notes", "search my docs", "what did I write about", "find in my vault", "check my index", "retrieve…
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.
my-wiki
Manage local OKF-compatible Markdown My Wiki vaults with an AI agent. Use for capturing webpages, PDFs, Office documents, notes, images, folders, and ZIP bundles as References; maintaining Reference-to-Concept evidence links; searching or answering from a vault; checking or repairing vault health; switching among…