Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/alrcatraz/astra-knowledge-base-mcpnpx agentmods add skills/alrcatraz/astra-knowledge-base-mcp/knowledge-base-interopWrote 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/alrcatraz/astra-knowledge-base-mcp/knowledge-base-interop)<a href="https://agentmods.dev/skills/alrcatraz/astra-knowledge-base-mcp/knowledge-base-interop"><img src="https://agentmods.dev/badge/skills/alrcatraz/astra-knowledge-base-mcp/knowledge-base-interop.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.01994 |
| Opus 5 | $0.00028 | $0.00997 |
| Sonnet 5 | $0.00011 | $0.00399 |
| Haiku 4.5 | $0.00006 | $0.00199 |
Grade A, and why
knowledge-base-interop 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 8d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base — LLM Wiki Interop
Two-layer knowledge architecture: LLM Wiki (curation layer, for humans) + Astra KB (search layer, for AI agents).
| Layer | What | For whom | Storage |
|---|---|---|---|
| Layer 1 — LLM Wiki | Curated Markdown pages with frontmatter, cross-refs | Humans (reading, browsing) | $WIKI_PATH — a directory of .md files |
| Layer 2 — Astra KB | Chunked, embedded text with SAG indexing | AI agents (search, retrieval) | PostgreSQL 16 + pgvector + pg_trgm |
Before You Begin
- LLM Wiki — ask the user where to create it; do not default to
~/wiki - Astra KB — MCP server with PostgreSQL backend (
scripts/run.sh) - Embedding API —
ASTRA_EMBED_BASE_URL+ASTRA_EMBED_API_KEY+ASTRA_EMBED_MODEL(default: SiliconFlow Qwen/Qwen3-VL-Embedding-8B) - MarkItDown MCP — document conversion
- watchdog (
pip install watchdog) — for realtime file watching
Architecture
Input (zip / path / file / URL)
│
├── classify + convert
│
▼ (Markdown)
┌──────────┴──────────┐
▼ ▼
┌──────────────┐ ┌──────────────┐
│ Layer 1: │ │ Layer 2: │
│ LLM Wiki │ │ Astra KB │
│ │ │ (direct) │
│ sync ────────┤──► │ │
│ watch ───────┤──► │ search │
└──────────────┘ └──────────────┘
Layer 1: LLM Wiki
wiki/
├── AGENTS.md (project-specific paths, conventions, sync commands)
├── index.md
├── mkdocs.yml (optional MkDocs config)
├── category_A/
├── category_B/
└── ...
Project-specific structure is always documented in AGENTS.md.
Layer 2: Astra KB
One KB per project (e.g. gliousa). Each contains:
chunks→embed_vec(pgvector) +pg_trgmindex for CJK ILIKEevents,entities,event_entities(SAG indexing, arxiv 2606.15971)
Search modes: hybrid, vector, fts, sag_fast, sag_precise
Pipeline 1: Wiki → KB sync
Batch import (all changed pages)
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.
- 8d ago First seen · 248 lines · 56 tokens per session scan A a9114347db83
knowledge-base-interop is a skill published in the GitHub repository alrcatraz/astra-knowledge-base-mcp (1 stars, last pushed 15d ago), licensed MIT. It adds 56 tokens to every session and 1,994 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 2026-08-30.
Other skills, from other repositories
llm-wiki-orient
Explain the LLM-Wiki pattern, its raw/wiki/schema architecture, how it differs from RAG, GraphRAG and agent memory, and what ready-made solution families exist. Use when the user asks what LLM-Wiki is, whether it is worth adopting, what OpenWiki/wiki memory means, or how the ecosystem fits together.
llm-wiki-local-first-stack
Design a local-first LLM-Wiki stack. Use when the user wants Markdown, git, Obsidian, ripgrep, local embeddings, qmd-style retrieval, SQLite/FTS/vector indexes, local LLMs, offline operation, or safe sync without cloud lock-in; route retrieval/index layer design to llm-wiki-retrieval-architect.
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
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…