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 tboome33/obsidian-mcp-router --skill wiki-querygit clone --depth 1 https://github.com/tboome33/obsidian-mcp-routerWrote 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/tboome33/obsidian-mcp-router/wiki-query)<a href="https://agentmods.dev/skills/tboome33/obsidian-mcp-router/wiki-query"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/wiki-query/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/tboome33/obsidian-mcp-router/wiki-query"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/wiki-query.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 | $0.00129 | $0.03099 |
| Opus 5 | $0.00064 | $0.01550 |
| Sonnet 5 | $0.00026 | $0.00620 |
| Haiku 4.5 | $0.00013 | $0.00310 |
Grade A, and why
wiki-query 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 7d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-query
Three-tier retrieval: cheap (hot cache) → cheap (index) → expensive (full pages + semantic search). Stop at the first tier that answers the question. Always cite the wiki pages used.
Pre-conditions
- Target vault has
wiki/scaffolding (hot.md,catalog.mdminimum). If not, tell the user the wiki isn't set up; offer thewikiskill. - Vault is online (
list_vaults).
Modes
The user may signal a preferred mode:
- quick — answer from hot.md alone if possible. Bail to standard if hot doesn't cover it.
- standard (default) — hot → index → 1-3 specific pages → synthesize.
- deep — hot → index → semantic search across the wiki → 5-10 pages → synthesize → file the answer back as a new wiki page.
If the user didn't say, infer: short factual question = quick; "explain X" = standard; "give me everything you know about X (from my wiki)" = deep.
Disambiguation note: "research X" is ambiguous — it could mean either (a) "tell me what my wiki has about X" (deep wiki-query) or (b) "go find new information about X on the web" (autoresearch). When the user says "research X" alone, ASK which they mean. Don't guess.
Steps
Tier 1: hot.md
mcp__obsidian-router__get_file({ vault, path: "wiki-meta/hot.md" })
Read it. If the cache contains the answer (the question is covered by the recent activity), answer from hot alone. Cite wiki-meta/hot.md as source. Stop.
If hot doesn't cover it: don't try to extract anything tangential. Move to tier 2.
Tier 2: catalog.md — IDF-weighted candidate ranking
mcp__obsidian-router__get_file({ vault, path: "wiki-meta/catalog.md" })
Score and rank index entries against the question using the algorithm below (the same one the router's src/helpers/idf-score.mjs module exposes for tools that need to score programmatically — keep the algorithm in sync so machine and skill agree).
Step 2a — Tokenise the query. Lowercase, split on non-letter/non-digit runs, drop tokens with length ≤2. Example: "What does my wiki say about position sizing?" → [what, does, wiki, say, about, position, sizing]. (Don't drop wiki / does etc. manually — IDF will down-weight them automatically.)
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.
- 7d ago First seen · 179 lines · 129 tokens per session scan A a8b2c286a47d
wiki-query is a skill published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed today), licensed Apache-2.0. It adds 129 tokens to every session and 3,099 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
librarian
Orchestrate vault knowledge workflows using the Librarian MCP server. Ingest solutions, search prior art, explore the knowledge graph, log daily learnings.
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).
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
mindbase
Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…
bastra-recall
Persistent external brain for ChatGPT, Codex, Claude, and other MCP clients — documents (PDFs, contracts, scans with OCR), personal facts (appointments, decisions, items, amounts), AND code lessons / preferences / project topology. USE PROACTIVELY in three modes. (1) RECALL — whenever the user asks about anything from…
bastra-recall
Proactive private local memory for ChatGPT and Codex — recall before acting, save durable rules, lessons and decisions without being asked. Requires the local bastra-recall MCP server installed by bastra install codex.