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 agentmods add skills/jkheadley/instar/knowledge-basenpx skills add JKHeadley/instar --skill knowledge-basegit clone --depth 1 https://github.com/JKHeadley/instarWhat 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 | $0.00058 | $0.01336 |
| Opus 5 | $0.00029 | $0.00668 |
| Sonnet 5 | $0.00012 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
knowledge-base scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:${INSTAR_PORT:-4040}/knowledge/ingest \ How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
knowledge-base -- Searchable Knowledge Base for Instar Agents
Build a searchable knowledge base from external sources -- URLs, documents, transcripts, PDFs. Uses the existing MemoryIndex (FTS5) for search, so no new dependencies.
How It Works
The knowledge base is a set of markdown files in .instar/knowledge/ that MemoryIndex indexes alongside your other memory files. Each file has YAML frontmatter for metadata and is tracked in a catalog for browsing.
.instar/knowledge/
catalog.json # Registry of all ingested sources
articles/ # Ingested web articles
transcripts/ # Video/audio transcripts
docs/ # Curated reference documentation
Ingesting Content
Via CLI
# Ingest text content directly
instar knowledge ingest "Article content here..." --title "My Article" --tags "AI,agents"
# Ingest from a URL (fetch first, then ingest)
# Step 1: Fetch the content
python3 .claude/scripts/smart-fetch.py "https://example.com/article" --auto > /tmp/fetched.md
# Step 2: Ingest it
instar knowledge ingest "$(cat /tmp/fetched.md)" --title "Article Title" --url "https://example.com/article" --tags "topic1,topic2"
Via API
curl -X POST http://localhost:${INSTAR_PORT:-4040}/knowledge/ingest \
-H "Content-Type: application/json" \
-d '{
"content": "The article content...",
"title": "Article Title",
"url": "https://example.com/article",
"type": "article",
"tags": ["AI", "infrastructure"],
"summary": "Brief description"
}'
Via Agent Workflow
When the agent wants to ingest content during a session:
- Fetch the content (WebFetch, smart-fetch, transcript tools, or Read for local files)
- Clean it (strip navigation, ads, boilerplate)
- Call the ingest API or write the file manually:
# Write the markdown file with frontmatter
cat > .instar/knowledge/articles/2026-02-25-my-article.md << 'EOF'
---
title: "My Article"
source: "https://example.com/article"
ingested: "2026-02-25"
tags: ["AI", "infrastructure"]
---
# My Article
[Cleaned article content here]
EOF
# Sync the index to pick up the new file
instar memory sync
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.
- 3d ago First seen · 190 lines · 0 tokens per session scan A 3b3ec59d32b1
knowledge-base is a skill published in the GitHub repository JKHeadley/instar (77 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 1,336 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
faiss
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance…
prompt-scanner
使用 agent-sec-cli 扫描 prompt 文本中的注入攻击和越狱尝试，返回结构化 JSON 扫描结果。当用户提到 prompt 安全、prompt 注入检测、越狱检测、提示词攻击检测，或者需要判断一段文本是否包含恶意 prompt 注入时，都应使用此技能。即使用户没有明确说"扫描"，只要涉及评估 prompt 文本的安全性，也应触发此技能。.
retrieval
Retrieval - vector DBs, embeddings, hybrid search, reranking.