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 auto-modegit 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/auto-mode)<a href="https://agentmods.dev/skills/tboome33/obsidian-mcp-router/auto-mode"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/auto-mode/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/auto-mode"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/auto-mode.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 | $0.00168 | $0.01943 |
| Opus 5 | $0.00084 | $0.00971 |
| Sonnet 5 | $0.00034 | $0.00389 |
| Haiku 4.5 | $0.00017 | $0.00194 |
Grade B, and why
auto-mode scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- *"ne demande plus rien"* / *"arrête de me demander à chaque fois"* / *"stop asking me"* — could mean `off` (no auto-save at all) OR `FullAuto` (auto-save without asking) OR `Hybrid` (auto-save the easy stuff, ask only How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auto-mode
Invoke the set_auto_enrich_mode MCP tool.
Modes — when to pick which
ClaudeAsk(default — propose, always confirm). Best for: discovering the feature, mixed-importance long sessions, vaults where false positives would be costly to clean up, calibration period.Hybrid(auto-save type-safe items like facts/URLs, ask on decisions/ADRs/techniques/rules). Best for: power-user sweet spot after a calibration week, active development with frequent URL ingestion, research with citations to pile up but conclusions to vet.FullAuto(auto-save everything; audit log inwiki-meta/journal.md+ sensitivity filter + hard cap that degrades toClaudeAskafter 5 saves/session). Best for: high-trust sessions, family chronicle / personal journal, long unsupervised flows (autoresearch, batch ingestion), solo brain-dumps where the wiki IS the conversation log. Session-scoped or host-scoped only (v0.89.0): this is the one mode a workspace.envmay not set. Ask for it here, or have it declared in the MCP host —persistwill not write it, and aFullAutositting in a project's file is refused at start-up (see below).off(no auto-suggestions; manual/saveonly). Best for: debugging sessions you don't want polluting the wiki, sensitive conversations, control-freak preference, default for legal/medical/financial vaults.
Argument parsing from $ARGUMENTS
- bare mode name (
ClaudeAsk,Hybrid,FullAuto,off) →mode=<name>, persist defaults to false <mode> --persistor"permanently"/"persist"/"de manière permanente"/"qui survit au restart"→persist=truemode=X persist=true— explicit form- Mode aliases accepted (case-insensitive):
ask→ ClaudeAsk ·auto/full/full-auto→ FullAuto ·semi/semi-auto/hybride→ Hybrid ·none/disable/disabled→ off
Natural-language phrase → mode mapping
When the user's intent is the BEHAVIOR rather than the mode name:
- "demande avant de sauver" / "ask before saving" →
ClaudeAsk - "auto-save les trucs sûrs" / "auto-save the cheap stuff" / "automatique sauf pour les décisions" →
Hybrid - "sauve tout automatiquement" / "save everything automatically" →
FullAuto - "arrête de sauver auto" / "stop auto-saving" / "désactive l'auto-enrichissement" / "pas de notes" →
off
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 Changed · +6 lines · +22 tokens per session 8d6f24f89606
- 11d ago First seen · 61 lines · 146 tokens per session scan B e1deaddbf366
auto-mode is a skill published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 168 tokens to every session and 1,943 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.