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 nealcaren/social-data-analysis --skill zotero-raggit clone --depth 1 https://github.com/nealcaren/social-data-analysisWrote 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/nealcaren/social-data-analysis/zotero-rag)<a href="https://agentmods.dev/skills/nealcaren/social-data-analysis/zotero-rag"><img src="https://agentmods.dev/badge/skills/nealcaren/social-data-analysis/zotero-rag/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/nealcaren/social-data-analysis/zotero-rag"><img src="https://agentmods.dev/badge/skills/nealcaren/social-data-analysis/zotero-rag.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 | $0.00045 | $0.01380 |
| Opus 5.5 | $0.00018 | $0.00552 |
| Sonnet 5.5 | $0.00009 | $0.00276 |
| Haiku 4.5 | $0.00005 | $0.00138 |
Grade A, and why
zotero-rag scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Library RAG: Semantic Search
Script paths below are relative to this skill's base directory ($SKILL_DIR), which Claude Code reports when the skill loads.
Semantic search over your local library of markdown-converted papers using sentence-transformers embeddings and ChromaDB.
Prerequisites
- uv installed (standard in this project)
- Papers ingested via
ingest.py(which converts to markdown, organizes files, and adds metadata toreferences.bib) references.bibwithmd_pathfields linking citation keys to markdown files
Important: Only files registered in references.bib are indexed. Loose markdown files in library/markdown/ without a bib entry will be flagged as "unlinked" during indexing. Run ingest.py to register them.
Quick Start
# Index your library (first time or after adding papers)
uv run "$SKILL_DIR"/scripts/rag.py index
# Search by meaning
uv run "$SKILL_DIR"/scripts/rag.py search "cultural capital and educational attainment"
Script Location
All commands use:
uv run "$SKILL_DIR"/scripts/rag.py <command>
Dependencies (sentence-transformers, chromadb) are auto-installed by uv on first run via PEP 723 inline metadata. No manual installation needed.
Commands
Index
Build or update the vector index from library/markdown/ files.
# Index all markdown files (incremental — skips unchanged files)
uv run "$SKILL_DIR"/scripts/rag.py index
# Index specific citation keys only
uv run "$SKILL_DIR"/scripts/rag.py index --keys Smith2020_Cultural Jones2019_Institutional
The index is stored at library/.rag-index/. First run downloads the all-MiniLM-L6-v2 embedding model (~80MB, cached by sentence-transformers).
Run this after adding new papers to keep the index current.
Search
Semantic search across all indexed documents. Returns JSON lines ranked by similarity.
uv run "$SKILL_DIR"/scripts/rag.py search "social movements and collective identity"
uv run "$SKILL_DIR"/scripts/rag.py search "interview methodology" --top-k 5
uv run "$SKILL_DIR"/scripts/rag.py search "Bourdieu field theory" --min-score 0.3
What ships with it
2 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.
- yesterday First seen · 153 lines · 45 tokens per session scan A 3ad65ac30985
zotero-rag is a skill published in the GitHub repository nealcaren/social-data-analysis (90 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 1,380 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.