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-lintgit 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-lint)<a href="https://agentmods.dev/skills/tboome33/obsidian-mcp-router/wiki-lint"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/wiki-lint/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-lint"><img src="https://agentmods.dev/badge/skills/tboome33/obsidian-mcp-router/wiki-lint.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 | $0.00119 | $0.10806 |
| Opus 5 | $0.00060 | $0.05403 |
| Sonnet 5 | $0.00024 | $0.02161 |
| Haiku 4.5 | $0.00012 | $0.01081 |
Grade A, and why
wiki-lint 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 today.
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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-lint
Read-only diagnostic. Surfaces problems and suggests fixes; never mutates the wiki without explicit confirmation.
Modes
The skill has three modes :
- Default (structural) — runs Checks A through H, plus N (decision-layer coherence), O (two folders named "Sessions"), P (prompt lifecycle) and Q (conventions drift). Cheap, scans page metadata + wikilinks + citations + two directory listings + the vault
CLAUDE.mdonly. The right mode for routine health checks. --deep(v0.15.0+, roadmap item #7') — also runs Checks I through L (plus Check J-bis, C11, which needs no digest — it reads the Smart Connections vector store and reports itself unavailable where there is none), which read the digest sidecars (wiki-meta/digests/<full-vault-path>— NESTED layout mirroringwiki/, review+ pass 3+ hardening) in bulk to detect cross-page redundancies, contradictions, and missing wikilinks. More expensive (reads N digests + N² comparisons in the worst case). Use after a long ingestion session or when you suspect the wiki has drifted. Enumeration MUST recurse —list_files({directory:'wiki-meta/digests'})returns immediate children only ; walk the tree to get every.mdunderneath.--okf <path>(v0.33.0+) — runs Check M ONLY : validates an OKF knowledge bundle (Google's Open Knowledge Format v0.1) against the spec's three conformance rules. The path is either a bundle exported bywiki-export --target okf(wiki-meta/exports/okf/<name>/inside a vault) or any local directory / cloned repo containing a third-party bundle. This mode doesn't lint the wiki itself.
Trigger phrases :
- "lint the wiki" / "health check" / "audit my wiki" → default mode
- "deep lint" / "find redundant concepts" / "detect contradictions" / "wiki-lint --deep" → deep mode
- "lint the wiki and fix what you can" → default mode with auto-fix offered for ERRORs
- "validate this OKF bundle" / "is this bundle conformant" / "check OKF conformance" / "wiki-lint --okf " → OKF mode
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.
- today Changed · +21 lines 61a0e76d1554
- yesterday Changed · +26 lines 348ecd4afaba
- 4d ago Changed · +18 lines 43a9b5ad1539
- 9d ago First seen · 332 lines · 119 tokens per session scan A 7131aba8d232
wiki-lint is a skill published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 119 tokens to every session and 10,806 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
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).
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
debug-memory
Query and manage the executable feedback debug memory.
mindbase
Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…
remem
Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.