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-workflowgit 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-workflow)<a href="https://agentmods.dev/skills/pvliesdonk/markdown-vault-mcp/vault-workflow"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/vault-workflow/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-workflow"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/vault-workflow.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 | $0.00040 | $0.00508 |
| Opus 5 | $0.00020 | $0.00254 |
| Sonnet 5 | $0.00008 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
vault-workflow 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 9d 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
Working effectively with the markdown vault
When the user mentions "my vault", "my notes", or asks a question that could be answered from their knowledge base, use the markdown-vault-mcp tools as follows.
Search strategy
- Default to
searchwithmode="hybrid"— combines BM25 keyword and embedding similarity, gives the best recall for conceptual questions. - Fall back to
mode="keyword"only when the user gives an exact phrase or tag they want matched literally. - If hybrid returns nothing and the query is a proper noun, retry with
mode="keyword"— embeddings miss exact names.
Reading and context
- After finding a relevant note with
search, callget_contexton the top hit before reading the full body. Context returns backlinks, outlinks, similar notes, folder peers, and tags in one call — usually enough to answer without reading the file. - Only call
readwhen the user asks for the text itself or whenget_contextdoes not give enough signal.
Link-graph questions
- "What notes reference X?" →
get_backlinks. - "What does this note link to?" →
get_outlinks. - "How are these two notes connected?" →
get_connection_path. - "What is orphaned?" →
get_orphan_notes. - "What is most cited?" →
get_most_linked.
Writes (only if read-only mode is disabled)
- Prefer
editoverwritefor targeted changes —editfails safely if the old text is not unique, preventing accidental overwrites. - Use
rename(update_links=True)for moves, neverwriteto a new path plusdeleteof the old path — theupdate_linksflag repairs internal references. - Never call
reindexafter writes; the server updates its index inline.
Do not
- Do not use
list_documentsas a search substitute — it is a flat enumeration, not ranked. - Do not read a note and then re-search for it; remember the path from the first result.
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.
- 9d ago First seen · 53 lines · 40 tokens per session scan A c210cf3d97f9
vault-workflow is a skill published in the GitHub repository pvliesdonk/markdown-vault-mcp (32 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 508 once invoked, about $0.0002 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…