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-designgit 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-design)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-design"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-design/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-design"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-design.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 | $0.00067 | $0.00884 |
| Opus 5 | $0.00034 | $0.00442 |
| Sonnet 5 | $0.00013 | $0.00177 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
llm-wiki-design 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki Design
Goal
Design a custom LLM-Wiki system that starts thin, stays inspectable and has explicit trust controls.
When to use
- The user wants to build their own LLM-Wiki implementation, CLI, Obsidian plugin, repo-docs agent, or team workflow rather than adopt an existing tool.
- A product decision is needed on data model, retrieval tier, provenance, storage, sync, review or agent integration before any code is written.
- The user asks for an MVP plan, architecture sketch, or build-vs-buy justification for a wiki/knowledge-base system.
- Do not use this skill to answer questions from an already-built wiki (route to a query skill instead) or to pick between existing off-the-shelf tools (route to
llm-wiki-choose).
Inputs
- Product/workflow goal.
- User type: personal, team, company, plugin, CLI, SaaS, research tool.
- Corpus type and scale.
- Local-first/privacy constraints.
- Target agents and editors.
- Required integrations.
Procedure
1. Frame the build-vs-buy reason
Custom build is justified when at least one is true:
- claim-level provenance is required;
- existing tools do not preserve human edits;
- local-first/offline operation is mandatory;
- team governance or permission model is specific;
- product UX is the main differentiator;
- corpus shape is unusual;
- integration with a workflow/repo/editor is central.
If none apply, recommend llm-wiki-choose again and prefer a ready-made path.
2. Define the domain model
Start with:
raw source -> source page -> entity/concept/comparison/synthesis/query pages
Define page types, lifecycle states, source hashes, claim types, review gates and protected sections.
3. Pick retrieval tier
Use the smallest sufficient tier:
| Tier | Use when |
|---|---|
| index + grep | first 50-100 sources or strong filenames/wikilinks |
| hybrid lexical + semantic | conceptual recall fails or corpus grows |
| graph-aware retrieval | relationships, provenance and multi-hop questions dominate |
| custom storage | product requirements demand concurrency, permissions or scale |
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 · 138 lines · 67 tokens per session scan A 1a1dd50e774e
llm-wiki-design is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 19d ago), licensed MIT. It adds 67 tokens to every session and 884 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
knowledge-base-interop
Two-layer knowledge architecture — curate in LLM Wiki, search in Astra KB. Covers input classification, source-to-wiki ingestion, wiki-to-KB export (batch + realtime), semantic chunking, SAG extraction, health checks, and multi-format export.
rag
Reports the state of your brain's search index — the RAG: how many notes and chunks are indexed, whether the live watcher is running, which embedder is in use, and the engine + index-schema versions. Re-indexes on demand too. The front door for the words owners reach for: '/rag', plus 'index status', 'is my index up…
adapter-authoring
Build a custom source → raw-intake adapter for Athenaeum. Use when someone wants to feed an external source (an API, an export file, a message feed, a scraper, another tool's output) into an Athenaeum knowledge base, asks "how do I write an adapter / integration for athenaeum", or wants to turn some data source into…
corpus-grounding-expander
Fetches and normalizes multi-version public-domain corpora into a single verified-axiom store for verbatim-relay grounding, recording per-version license and provenance.
brain
Health-check the second brain so failures are not silent: is the local search server alive, is the RAG index fresh, is the session-memory ledger filling, did the nightly distillation run. Read-only, with a green/red verdict per component. Triggers: "/brain", "/memory", "is the reindex alive".
read-search-smart
Semantic search via Smart Connections embeddings. Returns ranked chunks with cosine scores and breadcrumbs. Use when the query is conceptual (meaning, not literal substring). EN triggers: "find notes about X", "what do I have on X", "semantic search for X", "find concepts related to X", "notes similar to ". FR…