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-implementation-deep-divegit 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-implementation-deep-dive)<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.
<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>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 | $0.00086 | $0.01559 |
| Opus 5 | $0.00043 | $0.00779 |
| Sonnet 5 | $0.00017 | $0.00312 |
| Haiku 4.5 | $0.00009 | $0.00156 |
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.
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-skillsand 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. |
What ships with it
10 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.
- references/docs/13-ecosystem-matrix.md 13 KB
- references/docs/14-technology-stack.md 21 KB
- references/docs/15-implementation-deep-dive.md 25 KB
- references/docs/16-retrieval-architecture.md 22 KB
- references/docs/17-mcp-api-integration.md 19 KB
- references/docs/18-evaluation-methodology.md 19 KB
- references/docs/19-security-threat-model.md 23 KB
- references/docs/20-ingestion-pipelines.md 18 KB
- references/docs/21-publishing-export.md 15 KB
- references/templates/source-manifest.yaml 2.2 KB
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 · 160 lines · 86 tokens per session scan A 4ffdb432eec4
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.
Other skills, from other repositories
okf-harness-bootstrap
This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.
okf-harness
One Door routes OKF Harness workspace requests to exactly one internal workflow at a time.
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…
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…
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…