Borrowing it
Nothing to install: this file belongs to nknishio/LLM-Wiki-Multimodal-TWM-Agent-Skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nknishio/LLM-Wiki-Multimodal-TWM-Agent-Skill/main/.claude/skills/llm-wiki/SKILL.mdgit clone --depth 1 https://github.com/nknishio/LLM-Wiki-Multimodal-TWM-Agent-SkillWrote 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/nknishio/llm-wiki-multimodal-twm-agent-skill/llm-wiki)<a href="https://agentmods.dev/skills/nknishio/llm-wiki-multimodal-twm-agent-skill/llm-wiki"><img src="https://agentmods.dev/badge/skills/nknishio/llm-wiki-multimodal-twm-agent-skill/llm-wiki/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/nknishio/llm-wiki-multimodal-twm-agent-skill/llm-wiki"><img src="https://agentmods.dev/badge/skills/nknishio/llm-wiki-multimodal-twm-agent-skill/llm-wiki.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 | $0.00019 | $0.06795 |
| Opus 5 | $0.00010 | $0.03397 |
| Sonnet 5 | $0.00004 | $0.01359 |
| Haiku 4.5 | $0.00002 | $0.00679 |
Grade B, and why
llm-wiki scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo loginctl enable-linger $USER This is a copy
88% identical to llm-wiki — 163 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 659 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Karpathy's LLM Wiki
Build and maintain a persistent, compounding knowledge base as interlinked markdown files. Based on Andrej Karpathy's LLM Wiki pattern.
Unlike traditional RAG (which rediscovers knowledge from scratch per query), the wiki compiles knowledge once and keeps it current. Cross-references are already there. Contradictions have already been flagged. Synthesis reflects everything ingested.
Division of labor: The human curates sources and directs analysis. The agent summarizes, cross-references, files, and maintains consistency.
When This Skill Activates
Use this skill when the user:
- Asks to create, build, or start a wiki or knowledge base
- Asks to ingest, add, or process a source into their wiki — including non-Markdown documents (PDF, PPTX, DOCX, XLSX, HTML) and images
- Asks a question and an existing wiki is present at the configured path
- Asks to lint, audit, or health-check their wiki
- References their wiki, knowledge base, or "notes" in a research context
Wiki Location
Location: Set via WIKI_PATH environment variable (e.g. in ~/.hermes/.env).
If unset, defaults to ~/wiki.
WIKI="${WIKI_PATH:-$HOME/wiki}"
The wiki is just a directory of markdown files — open it in Obsidian, VS Code, or any editor. No database, no special tooling required.
Architecture: Three Layers
wiki/
├── SCHEMA.md # Conventions, structure rules, domain config
├── index.md # Sectioned content catalog with one-line summaries
├── log.md # Chronological action log (append-only, rotated yearly)
├── raw/ # Layer 1: Immutable source material
│ ├── articles/ # Web articles, clippings
│ ├── papers/ # PDFs, arxiv papers
│ ├── transcripts/ # Meeting notes, interviews
│ └── assets/ # Images extracted from sources, one subdir per source:
│ # assets/<source-slug>/img-1.png, img-2.png, ...
├── .llm-wiki/ # Agent-internal state (not a wiki layer)
│ └── image-caption-cache.json # SHA-256 → caption, dedups vision work
├── entities/ # Layer 2: Entity pages (people, orgs, products, models)
├── concepts/ # Layer 2: Concept/topic pages
├── comparisons/ # Layer 2: Side-by-side analyses
└── queries/ # Layer 2: Filed query results worth keeping
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.
- install.ps1 799 B runs code
- install.sh 822 B runs code
- pyproject.toml 863 B
- README.md 9.6 KB
- scripts/caption_cache.py 3.6 KB runs code
- src/llm_wiki/__init__.py 397 B runs code
- src/llm_wiki/caption_cache.py 2.4 KB runs code
- src/llm_wiki/cli.py 4.5 KB runs code
- src/llm_wiki/convert.py 3.9 KB runs code
- src/llm_wiki/images.py 2.8 KB runs code
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 · 659 lines · 19 tokens per session scan B 933236b5aa49
llm-wiki is a skill published in the GitHub repository nknishio/LLM-Wiki-Multimodal-TWM-Agent-Skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 6,795 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). It is 88% identical to llm-wiki, differing in 163 lines, and is treated as a copy.
Other skills, from other repositories
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
knowledge_store_skill
Skill for working with local .knowledge.yaml files via KnowledgeStore. Use this when you need to recall, search, or manage directory-local memories and knowledge links stored in plain YAML alongside the user's project files. KnowledgeStore is directory-scoped. Each directory that contains a .knowledge.yaml file…
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
openkb-deck-neon
A skill for creating a single-file HTML slide deck from content stored in OpenKB, a knowledge-base chat system. It defines a dark, high-tech visual style using neon colors, glow effects, and glass-like panels.
openkb-deck-editorial
A tool for creating a single-file HTML slide presentation from compiled knowledge-base content. Its visual style uses a warm cream background, serif typography, and brick-red accents.