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 savegit 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/save)<a href="https://agentmods.dev/skills/tboome33/obsidian-mcp-router/save"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/save/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/save"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/save.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 | $0.00112 | $0.04069 |
| Opus 5 | $0.00056 | $0.02034 |
| Sonnet 5 | $0.00022 | $0.00814 |
| Haiku 4.5 | $0.00011 | $0.00407 |
Grade A, and why
save 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
save
The most-used wiki skill. Turn the current conversation into a wiki page in seconds, with the right frontmatter and links so future queries find it.
When to use
- "save this" / "save that answer" — file the current turn or a recent thread as a polished, type-classified document
- "/save " — file with an explicit slug instead of inferred one
- "save this decision" / "ADR this" — file as a decision/ADR with that frontmatter type
⚠️
/saveno longer files towiki-meta/Sessions/(router v0.12.8+; waswiki/Sessions/in v0.12.4–v0.12.7). That folder is owned by thesession-auto-journal.mjshook which writes one chronological file per Claude Code session automatically AND auto-appends a 2-line summary (objectif + résultat) towiki-meta/journal.mdat SessionEnd. Use/savefor polished, type-classified outputs that deserve a permanent document — decisions, answers, references, techniques, ADRs, ideas. If the user says "save this session" or "save the whole conversation", redirect: the auto-journal already captures the raw chronology + a log summary; ask which polished insight they want to extract.
When NOT to use
- The user asks "save the file" referring to an actual file on disk → that's
Write/Edit, not this skill - The conversation has nothing worth saving (small talk, errors, abandoned attempt) → push back gently: "this conversation doesn't have a clear takeaway — what specifically should I save?"
- The user wants to ingest an external source → that's
wiki-ingest
Pre-conditions
- Target vault has
wiki/scaffolding (usewikiskill first if not). - Vault is online.
Steps
1. Identify what to save
Three flavors (the session flavor is deprecated — auto-journal hook owns chronological capture since v0.12.4):
- Specific answer — "save that answer". Capture the most recent substantive answer from you, with enough context for it to make sense alone. Type:
answer. - Specific insight — "save this decision" / "save this technique" / "ADR this". The user is pointing at a discrete thing. Type matches what they said (
decision,technique,idea,runbook,adr). - Reference / runbook — "save this as a ref" or the conversation produced a how-to. Type:
reference.
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 · 219 lines · 112 tokens per session scan A 0133b38eff67
save is a skill published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed today), licensed Apache-2.0. It adds 112 tokens to every session and 4,069 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.