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 wiki-foldgit 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/wiki-fold)<a href="https://agentmods.dev/skills/tboome33/obsidian-mcp-router/wiki-fold"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/wiki-fold/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/wiki-fold"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/wiki-fold.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 | $0.00125 | $0.02187 |
| Opus 5 | $0.00063 | $0.01094 |
| Sonnet 5 | $0.00025 | $0.00437 |
| Haiku 4.5 | $0.00013 | $0.00219 |
Grade A, and why
wiki-fold 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 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.
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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-fold
Append-only rollup of journal.md into hierarchical summary pages stored under wiki/folds/. Inspired by log-structured systems: small windows fold into bigger ones over time, and the log itself stays linear forever.
When to use
journal.mdhas grown past ~100 entries and needs structural summarization.- The user wants a "what happened in the last week / month" report.
- After a multi-source ingestion session: roll up the new entries into one fold page.
Pre-conditions
- Target vault has
wiki-meta/journal.md. - Vault is online.
Steps
1. Read the log
mcp__obsidian-router__get_file({ vault, path: "wiki-meta/journal.md" })
Parse it into structured entries. The format from the wiki and wiki-ingest skills is:
- YYYY-MM-DD HH:MM — <verb> — <target(s)> — <reason>
If a line doesn't parse, skip it but don't fail.
2. Determine the fold window
Default: fold the last 2^k entries where k is chosen so the window is between 8 and 64 entries. The user can override with an explicit window:
- "fold the last 16 entries" → k=4, 16-entry window
- "fold this week" → time-bounded, take all entries with timestamps in the last 7 days
- "fold the last month" → time-bounded, last 30 days
If none of those signals are given, default to the last 16 entries.
3. Group entries by verb and target
Extractive grouping (no invention):
- Group by
verb(ingest, scaffold, lint, fold, query-filed, ...) → count and list distinct targets - Group by target (which page was touched most often)
- Identify the time span: first timestamp, last timestamp
This is pure aggregation. Don't infer themes that aren't literally there.
4. Compute the fold page path
wiki/folds/<window-id>.md
Where <window-id> is:
- For count-based windows:
last-<N>-as-of-<YYYY-MM-DD> - For time-based windows:
<YYYY-MM-DD>--<YYYY-MM-DD>
The deterministic naming is what makes folds idempotent: re-running with the same window writes to the same path.
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 First seen · 168 lines · 125 tokens per session scan A 0429c90f1846
wiki-fold is a skill published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed today), licensed Apache-2.0. It adds 125 tokens to every session and 2,187 once invoked, about $0.0006 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 2026-09-03.
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-maintain
Orchestrates the recurring daily-maintenance loop for the PM wiki — registry-driven multi-source sweep, ingest, daily brief, brief rotation, and a health check — with explicit interactive-vs-autonomous mode handling.
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).
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
okf-pro
Operating rules for the .okf/ knowledge bundle — filing new concepts, the board, the journal, the daily snapshot, closing work, source attribution, and the generated/verified attestation policy. Use before reading from or writing anything into .okf/.
harness-step3-session-management
A project setup for keeping an agent’s work state in files between separate chat sessions. It creates a task list, a progress summary, and a script for checking the project environment.