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/wiki-boundary)<a href="https://agentmods.dev/commands/tboome33/obsidian-mcp-router/wiki-boundary"><img src="https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/wiki-boundary/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/wiki-boundary"><img src="https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/wiki-boundary.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 | $0.00058 | $0.00572 |
| Opus 5 | $0.00029 | $0.00286 |
| Sonnet 5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
wiki-boundary 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 11d 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 wiki-boundary skill.
Default behaviour:
- Pre-req: the knowledge graph
wiki-meta/graph/knowledge-graph.jsonmust exist AND carry substance measurements (run/wiki-graphfirst if the tool refuses). - Calls the read-only
find_boundary_pagesMCP tool: one query over the persisted graph, no page reads, nothing written. - Score = inbound links damped by length (
inbound / (1 + words/100): full weight on an empty page, halved at 100 words, a tenth at 900), multiplied ×1 → ×2 for staleness. Same graph ⇒ same ranking, always. - Pages typed
redirect/source/answerare held out by default (thin is their job); the count held out is always reported. - On a vault you have not run this on before, calibrate the exemptions first — those defaults are one vault's vocabulary, and they are what keeps the ranking meaningful. Measured: DEDIBOX's top hit was a migration stub typed
index, which the defaults do not catch. - Report
graphAnalyzedAt— a stale graph ranks pages that may no longer exist.
Arguments:
[--limit N]— how many pages to show (default 10, ceiling 100).[--min-inbound N]— ignore pages with fewer inbound links (default 1).[--exempt-types a,b,c]— REPLACES the default exemption list, so pass the defaults plus your additions.[--exempt-statuses a,b,c]— hide pages by frontmatterstatus:(e.g.superseded). NO default: closed pages stay visible and labelled (statusis on every row); hiding them is per-vault calibration, named in the report.[--all-types]— score every page, exemptions off. Expect migration stubs to dominate.[--as-of YYYY-MM-DD]— measure recency against this date instead of the graph's build stamp.
Always state that the score proposes attention, it does not establish importance, and that index/hub pages legitimately appear near the top.
See roadmap-emprunts §2.17 item C10.
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.
- 11d ago First seen · 26 lines · 58 tokens per session scan A 628cc2e01ae9
wiki-boundary is a command published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 572 once invoked, about $0.0003 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
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-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-discover
Auto-discover new sources from the web. Searches based on config topics and known knowledge gaps.
wiki-status
Show wiki health overview — source count, page stats, orphan count, last activity dates.
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
ask
Query the MindBase wiki — cited answer using hybrid search + graph expansion. Usage: /mb:ask [-p ] [--all-projects].