llm-wiki-implementation-deep-dive

llm-wiki-implementation-deep-dive is a skill for Claude Code, Codex from po4yka/llm-wiki-skills. It costs 86 tokens per session (1,559 once invoked), scanned A, original, MIT.

An architecture comparison of open-source LLM-Wiki implementations, which are systems that organize information for language-model and coding-agent use.

In plain words
What is it for?
It is for comparing projects such as OpenWiki, RepoAgent, Obsidian plugins, and session-transcript wikis by architecture, readiness, licensing, privacy, and reusable design patterns.
Why use it?
It helps developers understand how existing projects are built and judge which patterns are suitable for production or a custom system.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for comparing projects such as OpenWiki, RepoAgent, Obsidian plugins, and session-transcript wikis by architecture, readiness, licensing, privacy, and reusable design patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/po4yka/llm-wiki-skills/llm-wiki-implementation-deep-dive
Install

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.

Any agent
npx skills add po4yka/llm-wiki-skills --skill llm-wiki-implementation-deep-dive
Clone the repo
git clone --depth 1 https://github.com/po4yka/llm-wiki-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for llm-wiki-implementation-deep-dive

README.md
[![agentmods](https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-implementation-deep-dive/github.svg)](https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-implementation-deep-dive)
Your own site
<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-implementation-deep-dive"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-implementation-deep-dive/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.

agentmods 80×15 button for llm-wiki-implementation-deep-dive

Your own site · 80×15
<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-implementation-deep-dive"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-implementation-deep-dive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,559 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.01559
Opus 5 $0.00043 $0.00779
Sonnet 5 $0.00017 $0.00312
Haiku 4.5 $0.00009 $0.00156

Measured 11d ago against content hash 4ffdb432eec4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

llm-wiki-implementation-deep-dive 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.

skills/llm-wiki-implementation-deep-dive/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM-Wiki Implementation Deep Dive

Goal

Produce an implementation-level comparison of existing open-source LLM-Wiki systems and extract reusable architecture patterns for a user's adoption plan or custom build.

When to use

  • The user asks for an implementation deep dive, architecture comparison, or "what to copy from" for OpenWiki, nashsu/llm_wiki, Vouch, RepoAgent, llm-wiki-compiler, SwarmVault, Obsidian LLM-Wiki plugins, or session-transcript wikis.
  • The user is deciding between a repo-docs generator, a full local-first desktop wiki, a review-gated agent-memory system, a compiler-first system, an Obsidian-native workflow, or a session-transcript wiki archetype.
  • The user wants production-readiness or licensing guidance before embedding one of these projects.
  • The user maintains llm-wiki-skills and wants the ecosystem/stack/deep-dive reference docs refreshed with newly re-verified facts.

Inputs

  • User use case: repo docs, personal local-first wiki, governed team wiki, product/reference implementation, Obsidian workflow, session-transcript wiki.
  • Candidate projects if named.
  • Required comparison dimensions.
  • Sensitivity/privacy constraints.
  • Whether the user wants recommendation, design patterns, or PR/documentation updates.

Procedure

1. Re-check current upstream facts

Before making current claims, browse official upstream sources for each named project:

  • README and docs;
  • release/activity/issue signals;
  • license;
  • install path;
  • storage layout;
  • retrieval/indexing implementation;
  • MCP/API surfaces;
  • review/provenance model;
  • security and eval docs.

If you cannot verify a current fact, mark it verify-before-use.

2. Classify the project archetype

Use these archetypes:

Archetype Examples Primary fit
Repo-docs generator langchain-ai/openwiki, OpenBMB/RepoAgent Codebase documentation and coding-agent context.
Full local-first desktop wiki nashsu/llm_wiki Personal/local knowledge operating system.
Review-gated agent memory vouchdev/vouch Team or governed knowledge where agents propose and humans approve.
Compiler-first knowledge system atomicstrata/llm-wiki-compiler, smaller compiler projects Typed, cited, linted, queryable compiled wiki artifacts.
Obsidian-native workflow green-dalii/obsidian-llm-wiki, other Obsidian plugins Vault-native human editing and graph-aware retrieval.
Session-transcript wiki Pratiyush/llm-wiki Agent session history as raw source material.
Graph-heavy local vault swarmclawai/swarmvault Broad ingestion, graph export, context packs and agent handoff.

Read the full file on GitHub · 160 lines

Changes

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.

  1. 11d ago First seen · 160 lines · 86 tokens per session scan A 4ffdb432eec4

Subscribe to this mod's changes

llm-wiki-implementation-deep-dive is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 18d ago), licensed MIT. It adds 86 tokens to every session and 1,559 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

okf-harness-bootstrap

This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.

pumblus/okf-harness · 0 tokens

okf-harness

One Door routes OKF Harness workspace requests to exactly one internal workflow at a time.

pumblus/okf-harness · 0 tokens

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…

tboome33/obsidian-mcp-router · 119 tokens

meta-sync-template

Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…

tboome33/obsidian-mcp-router · 159 tokens

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…

tboome33/obsidian-mcp-router · 112 tokens

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…

tboome33/obsidian-mcp-router · 129 tokens