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/who-is-speaking)<a href="https://agentmods.dev/commands/tboome33/obsidian-mcp-router/who-is-speaking"><img src="https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/who-is-speaking/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/who-is-speaking"><img src="https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/who-is-speaking.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 | $0.00087 | $0.00352 |
| Opus 5 | $0.00044 | $0.00176 |
| Sonnet 5 | $0.00017 | $0.00070 |
| Haiku 4.5 | $0.00009 | $0.00035 |
Grade A, and why
who-is-speaking 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 12d 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 who-is-speaking skill.
ARGUMENTS: $ARGUMENTS
Required: the family member's name or one of their accepted aliases (e.g., "Roland", "roro", "papa", "Karine", "max", "nico", …) — passed via $ARGUMENTS above. If omitted, the skill will ASK the user explicitly before guessing.
The skill handles:
- Reading the vault's
CLAUDE.mdfor the canonical members + aliases table (per-vault — never hardcoded) - Case-insensitive matching against canonical names AND aliases
- Refusing to guess when no match — pushes back with the canonical list
- Locking the router to the family vault (
lock_vault) + settingHybridauto-enrich mode (set_auto_enrich_mode) after a successful match - Re-identification mid-session ("c'est " / "switch to ") without unlocking
- Push-back when the current default vault doesn't have the
tribu-routingconvention installed
Best paired with the tribu-routing convention. Install on a vault via /obsidian-router:conventions install tribu-routing then customize the members table in the vault's CLAUDE.md.
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.
- 12d ago First seen · 20 lines · 87 tokens per session scan A b853a18c3d34
who-is-speaking is a command published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 87 tokens to every session and 352 once invoked, about $0.0004 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 2026-08-31.
Other commands, from other repositories
obsidian-catchup
Review and process everything captured on the go from the Telegram journal bot - voice, text, images, PDFs, links - waiting in the catchup queue. You pull it when you are back at the laptop; nothing is processed autonomously.
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.
wiki-req
Capture and decompose a concept into atomic, traceable wiki requirements. Clarifies ambiguous requirements, splits them into atomic pieces, and persists them as wiki/requirements/ pages with status tracking.
wiki-record
Capture the just-completed task's tool-call trajectory into the wiki as agent working-memory, then optionally distill it into a reusable skill.
wiki-retro
Save an atomic insight from the current task into the wiki. Creates a single markdown file that layered recall surfaces in future sessions.
wiki-run
Run the full wiki cycle: discover → ingest → lint. Optionally schedule for auto-updates.