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.
git 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/commands/tboome33/obsidian-mcp-router/conventions)<a href="https://agentmods.dev/commands/tboome33/obsidian-mcp-router/conventions"><img src="https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/conventions/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/commands/tboome33/obsidian-mcp-router/conventions"><img src="https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/conventions.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 | $0.00036 | $0.00596 |
| Opus 5.5 | $0.00014 | $0.00238 |
| Sonnet 5.5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
conventions 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 29d 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
Invoke the conventions skill to manage CLAUDE.md conventions in one or more Obsidian vaults.
Sub-commands:
list— show available conventions + which are installed on the target vault(s)install <id>[,<id>…] [on <vault>] [--all]— append one or more conventions to the target vault(s)' conventions file, one guardedinstall_conventionscall per vault, verified by reading the file back (languagescarries the vault's own value, so it is asked per vault and never installed with--all)remove <id> [on <vault>] [--all] [confirm:true]— strip a convention's section from the target vault(s)' CLAUDE.mdsync-all-vaults <id>— convenience alias forinstall <id> --allmigrate-bilingual [on <vault>]— replace the retiredbilingualconvention withlanguages(the value is asked; preview, backup andifMatchwrite, one vault at a time)
Convention ids are the file names in skills/conventions/snippets/<id>.md (14 at the time of writing). The live list is what install_conventions with dryRun: true and ids: [] returns in catalogue — the router reads it from its own package. Since 2026-09-26 bilingual is retired (skills/conventions/retired/, recognised and removable, never installed — the tool reports it in retired) and languages — which carries the vault's own list of languages — takes its place.
⚠️ Safety on remove (v0.8.12, NIT-4 + IMP-4)
remove is destructive — it strips a section identified by its H2 heading. If you've hand-edited the convention's section in your vault's CLAUDE.md (extended it with personal rules), removal will wipe your customisations.
Mandatory guards enforced by the skill:
- Preview before write — the exact content to remove is shown to you BEFORE any disk write.
- Sidecar backup — a copy of the unmodified
CLAUDE.mdis written toCLAUDE.md.bak-<id>-<timestamp>in the same vault before the destructivewrite_file. Backups are NEVER auto-cleaned. confirm:truerequired for--all— bulk removals refuse to proceed without an explicit confirmation argument. Single-vault removals can proceed after preview.
ARGUMENTS: $ARGUMENTS
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.
- 29d ago Changed dbf9c42c1afd
- 1mo ago Changed · +1 lines 713f283f222f
- 2mo ago First seen · 25 lines · 36 tokens per session scan A fbb1d67fe6c9
conventions is a command published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 596 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.
wiki-digest
Generate a daily or weekly digest of wiki changes — new sources, pages, insights, and gaps.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
wikimate-link
A command for connecting related Obsidian notes with [[links]] or grouping notes into a topic table of contents, also called a MOC. Obsidian is an app for storing linked Markdown notes.
brief
Cold-start session orientation — use when starting fresh or returning after a long absence (days or weeks). Scales depth to how long you've been away. Not for quick mid-session checks (use /tools:status) or planning (use /tools:overview).