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 SantiagoBobrik/llm-wiki-kit --skill wiki-searchgit clone --depth 1 https://github.com/SantiagoBobrik/llm-wiki-kitWrote 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/santiagobobrik/llm-wiki-kit/wiki-search)<a href="https://agentmods.dev/skills/santiagobobrik/llm-wiki-kit/wiki-search"><img src="https://agentmods.dev/badge/skills/santiagobobrik/llm-wiki-kit/wiki-search/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/santiagobobrik/llm-wiki-kit/wiki-search"><img src="https://agentmods.dev/badge/skills/santiagobobrik/llm-wiki-kit/wiki-search.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 | $0.00051 | $0.00731 |
| Opus 5 | $0.00026 | $0.00365 |
| Sonnet 5 | $0.00010 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
wiki-search 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-search
Searches Wiki/ for articles relevant to a query and returns a synthesized answer drawn from the user's own knowledge base.
Arguments — parse $ARGUMENTS:
--vault <name>or--vault=<name>— explicit vault. Pass.to mean "the vault at cwd" (resolved against the pre-loaded list).- Everything else in
$ARGUMENTS, after removing the flag and its value, is the query — the topic, term, or question to search for. If empty, infer from the conversation context.
Vault resolution (only when --vault is absent):
- Read the pre-loaded vault list:
- Exactly one vault → use it. Do not ask.
- Two or more → ask via
AskUserQuestion. - None → bail; Obsidian isn't running.
--vault . handling: resolve the current working directory against the pre-loaded vault list. If cwd matches a registered vault path, use that vault's name. Otherwise bail — cwd isn't a vault.
Pre-loaded Context
Registered Obsidian vaults (name<TAB>path per line):
!obsidian vaults verbose
Workflow
0. Select the target vault
Parse the pre-loaded vault list (name<TAB>path per line). Apply the Vault rule from the top of this file to pick one. Hold the chosen vault's <name> and absolute <path> — every subsequent step uses them.
If <path>/Wiki/ or <path>/Wiki/index.md is missing, print ℹ️ Vault not wiki-initialized. Run /wiki-init to bootstrap. and stop.
1. Match against the index
Read the chosen vault's index — open <path>/Wiki/index.md with the Read tool.
Scan it for entries whose title or hook phrase relate to the query. Cast a wide net — partial matches, synonyms, and related concepts all count.
2. Read matching articles
Read the full content of every matched article. If no index entry matches, fall back to:
obsidian vault=<name> search query="<query keywords>" path="Wiki" limit=5
Then read the results.
3. Answer from the content
Synthesize a clear, direct answer using only what the Wiki contains. Rules:
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 · 71 lines · 51 tokens per session scan A e628f26aed3f
wiki-search is a skill published in the GitHub repository SantiagoBobrik/llm-wiki-kit (10 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 731 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…