Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tboome33/obsidian-mcp-routernpx agentmods add skills/tboome33/obsidian-mcp-router/meta-sync-templateWrote 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/meta-sync-template)<a href="https://agentmods.dev/skills/tboome33/obsidian-mcp-router/meta-sync-template"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/meta-sync-template/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/meta-sync-template"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/meta-sync-template.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 | $0.00159 | $0.05147 |
| Opus 5.5 | $0.00064 | $0.02059 |
| Sonnet 5.5 | $0.00032 | $0.01029 |
| Haiku 4.5 | $0.00016 | $0.00515 |
Grade A, and why
meta-sync-template 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 26d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
meta-sync-template
Interactive bulk propagation of the reference vault (typically .template) to one or more configured vaults. Conversational picker over scripts/setup-vault.mjs's --sync-all and --sync-plugins modes with up-front diagnostics (online/offline status, REST-API-plugin presence per target).
Which command runs (moved out of the frontmatter, which the Agent Skills spec caps at 1024 characters): the router config comes from the OBSIDIAN_ROUTER_CONFIG env var, defaulting to ~/.claude/obsidian-mcp-router/config.json. The all-vaults case runs npm run setup-vault -- --sync-all (the script auto-skips the reference vault and refuses to leak credentials); subsets loop scripts/setup-vault.mjs <path> --sync-plugins. Flagging a missing obsidian-local-rest-api before anything runs lets the user bootstrap that vault first rather than meet a runtime warning mid-sync.
Safety: as of obsidian-mcp-router v0.11.2+, the underlying script itself enforces every safety invariant this skill cares about — it refuses to sync the reference vault onto itself (case-insensitive on Windows / macOS), and it refuses to first-time-copy obsidian-local-rest-api into a target lacking it (the copy would clone the reference's data.json and leak the API key). The skill's role is purely UX: a friendly picker, clear pre-flight info, per-vault aggregation. The hard safety guarantees live in setup-vault.mjs (samePath() check at syncPluginsMode entry; CREDENTIAL_LEAK_PLUGINS skip in the plugin loop; case-insensitive self-skip in --sync-all). See tests/setup-vault-safety.test.mjs for the regression coverage.
What the underlying script propagates
From referenceVault to each target vault:
- Plugin folders:
.obsidian/plugins/<plugin-id>/— full directory copy when the plugin is missing from the target, or a re-clone with--forcethat preserves the target's localdata.json. A source folder may hold CODE (main.js+manifest.json) or only a settings pre-seed (data.json); the report tells them apart (see step 7). - Plugin enablement:
community-plugins.jsonentries appended for every plugin copied for the first time — code or settings only — so a plugin switches on as soon as its code arrives. Those ids are listed on purpose and are not counted as synced. - CSS snippets:
.obsidian/snippets/*.css+ enabled inappearance.json(idempotent) - Root docs:
README.md,Documentation/(the quick-reference PDFs,SETUP.md),.claude/(preserved if already present unless--force; under--forcea folder is MERGED, never wiped first). Two things never travel,--forceor not: a backup (*.bak,*.bak-*— the reference vault's history, not the target's), and the reference vault's conventions file (Documentation/CLAUDE.md) into a vault that already has one at any of the three candidate locations — a second file would leave the vault ambiguous, which is what the 2026-09-22 sync did to 13 vaults. A vault with no conventions file still receives the template's. The run prints each entry it left out and why. One more thing never travels: when the source is the shipped skeleton (the bundledtemplates/reference-vault-skeleton, or the one--sync-from-githubextracts), itsREADME.mdis not copied — it documents the skeleton, not the vault. - Smart Connections — first-time only:
.smart-env/smart_env.json+ embedding-model cache are cloned only when the target's.smart-env/directory is entirely missing (planSmartEnv()/syncPluginsMode()inscripts/setup-vault.mjs,force: false). On an already-bootstrapped target,--sync-plugins --forcedoes NOT refresh.smart-env, and--langdoes not rewrite it either. To push an updated Smart Connections config to an existing target, delete the target's whole.smart-env/directory (the check is on the directory, not on the file; the embedding cache is rebuilt on the next Smart Connections start) before re-running, or re-bootstrap the vault. - Embedding model by language —
--lang <code>(on--sync-pluginsand--sync-all) picks the model of the.smart-envthe sync creates:enkeepsTaylorAI/bge-micro-v2, any other language gets the multilingualonnx-community/embeddinggemma-300m-ONNX(zh:Xenova/jina-embeddings-v2-base-zh), andlanguageis set to match. Without--lang, a language the vault already declares is used (thelanguagesconvention in its CLAUDE.md → its first code; the retiredbilingualconvention →fr; orlanguagein Smart Connections' settings); otherwise the source's model is kept and a one-line hint says to pass--langfor a non-English vault. The keys come from Smart Connections' own adapter table — seesrc/helpers/smart-env-language.mjs.
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.
- 26d ago Changed · +11 lines bf839f2cd3c2
- 1mo ago Changed ab8146991274
- 1mo ago First seen · 193 lines · 159 tokens per session scan A ebbd503b50bd
meta-sync-template is a skill published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 159 tokens to every session and 5,147 once invoked, about $0.0006 per session on Opus 5.5. 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
unanswered-messages
Scan WhatsApp + Gmail for messages still awaiting MY reply — the ones that need nothing more than an answer, so they spin off no case, reminder, or event and get forgotten — record each on the board as an unanswered message, and mark it answered the moment I reply (so it leaves the view). Use when the user says "what…
fitness-training-plan
The Fitness coach's HEADLINE skill — generate a personalised WEEKLY TRAINING PLAN for the athlete with deliberate VARIETY / ROTATION (rotate sports and intensity; alternate hard/easy; progressive overload toward the goal date), then PERSIST it via savetrainingplan so it lands on the /fitness/training-plan history…
librarian
Orchestrate vault knowledge workflows using the Librarian MCP server. Ingest solutions, search prior art, explore the knowledge graph, log daily learnings.
reminders-review
The reminder janitor — a periodic sweep that reviews every OPEN reminder on the board and CLOSES the ones whose job is already done or whose moment has passed, so the reminders list stays a live to-do surface instead of a graveyard of stale nudges. It reads each reminder's full context via the board MCP, then sorts it…
fitness-pre-workout-brief
Prepare and persist TODAY'S pre-workout / training-readiness brief — the daily "should I train today?" call. It reads the board's deterministic FORM SCORE (0–100, with its hrv / sleep / resting-HR / load breakdown), folds in last night's sleep + this morning's metrics + recent training load + the athlete profile +…
usage-guard
Arm proactive 5-hour usage protection for long Claude Code sessions (batch, subagents, high window % at start). Daemon reads account-level 5-hour window usage (not per-session). User types /usage-guard at session start. Re-arm every sitting. If user mentions usage-guard by name, read this file and run arm.sh.