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 po4yka/llm-wiki-skills --skill llm-wiki-setupgit clone --depth 1 https://github.com/po4yka/llm-wiki-skillsWrote 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/po4yka/llm-wiki-skills/llm-wiki-setup)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-setup"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-setup/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/po4yka/llm-wiki-skills/llm-wiki-setup"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-setup.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 | $0.00070 | $0.01014 |
| Opus 5 | $0.00035 | $0.00507 |
| Sonnet 5 | $0.00014 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
llm-wiki-setup 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki Setup
Goal
Turn a chosen LLM-Wiki recommendation into a working setup with safe defaults.
When to use
- The user has already picked a target vault/architecture and wants it turned into a working setup (directories, templates, skills installed).
- Configuring
AGENTS.md/CLAUDE.md, hooks, or git/PR review policy for an LLM-Wiki workflow. - Connecting a coding agent (Claude Code, Codex, Cursor, OpenCode) to Agent Skills so
wiki-ingest/wiki-query/wiki-lintwork. - Migrating an existing Obsidian vault or repository docs tree into the raw/wiki/schema model.
- Not for a guided first-demo walkthrough with no prior architecture decision — route that to
llm-wiki-zero-to-working-wikiinstead.
Inputs
- Chosen solution or target architecture.
- Project/vault path.
- Target agent(s): Claude Code, Codex, Cursor, OpenCode, etc.
- Privacy/local-first constraints.
- Existing docs or empty start.
Procedure
1. Confirm the setup target
Identify one target:
- local-first Markdown vault;
- existing Obsidian vault;
- repository documentation wiki;
- qmd/hybrid-search upgrade;
- team PR-based workflow;
- custom product/CLI/plugin.
If the target is an external tool, browse official installation docs before giving commands.
2. Preflight
Check or ask for:
- git initialized;
- backup or branch available;
- package managers available;
- agent skill installation target;
- whether writes should be direct, dry-run, or PR-based;
- sensitive material that must not leave the machine.
3. Create the vault shape
Default structure:
raw/sources/
raw/assets/
inbox/
wiki/index.md
wiki/log.md
wiki/sources/
wiki/entities/
wiki/concepts/
wiki/comparisons/
wiki/synthesis/
wiki/queries/
_agent/reports/
_meta/schemas/
Start wiki/index.md and wiki/log.md from the bundled references/templates/wiki/ starters; prefer the target repository's own vault templates when they already exist.
4. Install skills
For Agent Skills-compatible agents, use commands like:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 147 lines · 70 tokens per session scan A 51a2d83a4bbc
llm-wiki-setup is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 18d ago), licensed MIT. It adds 70 tokens to every session and 1,014 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
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
wiki-export
Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…
wiki-query
Answer a question using ONLY the existing wiki vault as the knowledge base — no web search, no general LLM knowledge. Reads hot.md first (cheap recent context), then catalog.md to navigate, then drills into specific pages, then optionally semantic-searches the wiki, and synthesizes an answer with citations. Use when…
wiki-fold
Roll up the wiki's journal.md entries into structured fold pages — like 2^k log compaction. Reads the last 2, 4, 8, 16... entries and writes a fold page that summarizes them by extractive summarization (no invention), with backlinks to children. Idempotent at the structural level — re-running with the same window…
wiki
Bootstrap or check a Karpathy-style "LLM wiki" structure inside an Obsidian vault — a self-maintaining knowledge base where pages reference each other and the LLM keeps it tidy. Sets up catalog.md (curated page catalog), journal.md (append-only operation history), hot.md (recent-context cache), and overview.md…