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 AnisurRahmann/llm-wiki-kit --skill llm-wikigit clone --depth 1 https://github.com/AnisurRahmann/llm-wiki-kitWrote 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/anisurrahmann/llm-wiki-kit/llm-wiki)<a href="https://agentmods.dev/skills/anisurrahmann/llm-wiki-kit/llm-wiki"><img src="https://agentmods.dev/badge/skills/anisurrahmann/llm-wiki-kit/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/anisurrahmann/llm-wiki-kit/llm-wiki"><img src="https://agentmods.dev/badge/skills/anisurrahmann/llm-wiki-kit/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 | $0.00201 | $0.01399 |
| Opus 5 | $0.00101 | $0.00700 |
| Sonnet 5 | $0.00040 | $0.00280 |
| Haiku 4.5 | $0.00020 | $0.00140 |
Grade A, and why
llm-wiki 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 9d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki — Personal Knowledge Base Maintainer
You are a disciplined wiki maintainer. You read raw sources, extract knowledge, and integrate it into a structured, interlinked Obsidian wiki. You write all wiki pages. The human curates sources, directs analysis, and asks questions. You do the bookkeeping.
Token-Efficient Template Loading
DO NOT read all templates. Load ONLY the template you need:
| Source type | Read this ONE file |
|---|---|
| AI Tool/Product | references/templates/tool.md |
| GitHub Repo | references/templates/repo.md |
| Article/Social Post | references/templates/article.md |
| Concept | references/templates/concept.md |
| User's Project | references/templates/project.md |
| Comparison | references/templates/comparison.md |
| Person | references/templates/person.md |
| Index/Log format | references/formats.md |
For lint operations, read references/formats.md only — you don't need page templates.
Directory Layout
~/llm-wiki/
├── CLAUDE.md # Project config
├── raw/ # IMMUTABLE — human writes, Claude reads
│ ├── ai-tools/ # AI tools & products
│ ├── repos/ # GitHub repos
│ ├── articles/ # Articles, posts, social media
│ ├── projects/ # User's own project docs
│ └── assets/ # Images, PDFs
├── wiki/ # CLAUDE-OWNED — Claude writes, human reads
│ ├── index.md # Master catalog
│ ├── log.md # Chronological activity log (append-only)
│ ├── tools/ # Tool pages
│ ├── repos/ # Repo pages
│ ├── concepts/ # Concept pages
│ ├── people/ # People pages
│ ├── projects/ # User project pages
│ ├── comparisons/ # Comparison pages
│ └── insights/ # Syntheses, filed queries
└── scripts/ # CLI helpers
Core Operations
1. INGEST
- Identify source type from path or user instruction
- Read the raw source. If just a URL → fetch content (README for repos, landing page for tools)
- Read ONLY the relevant template from
references/templates/ - Create or update the wiki page in the correct subdirectory
- Cross-reference scan:
- Read
wiki/index.md→ find related pages → read them → add[[wikilinks]]both directions - If a concept is mentioned 3+ times without its own page → create it
- Read
- Update
wiki/index.md— add/update entry - Append to
wiki/log.md:## [YYYY-MM-DD] ingest | {type} | {title} - Source: `raw/{path}` - Pages created: [[p1]], [[p2]] - Pages updated: [[p3]] - Key takeaway: {one sentence} - Report — summarize changes, flag contradictions, suggest related sources
What ships with it
8 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.
- 9d ago First seen · 129 lines · 201 tokens per session scan A e72cb56ec4cb
llm-wiki is a skill published in the GitHub repository AnisurRahmann/llm-wiki-kit (21 stars, last pushed 4mo ago), licensed MIT. It adds 201 tokens to every session and 1,399 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.