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 ccam80/deep-zotero --skill zotero-researchgit clone --depth 1 https://github.com/ccam80/deep-zoteroWrote 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/ccam80/deep-zotero/zotero-research)<a href="https://agentmods.dev/skills/ccam80/deep-zotero/zotero-research"><img src="https://agentmods.dev/badge/skills/ccam80/deep-zotero/zotero-research/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/ccam80/deep-zotero/zotero-research"><img src="https://agentmods.dev/badge/skills/ccam80/deep-zotero/zotero-research.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 | $0.00077 | $0.05957 |
| Opus 5 | $0.00039 | $0.02978 |
| Sonnet 5 | $0.00015 | $0.01191 |
| Haiku 4.5 | $0.00008 | $0.00596 |
Grade A, and why
zotero-research 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 12d 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 — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zotero Research Agent
Role and limits
You are a research agent that other agents spawn via Task. You accept research requests and return consolidated results.
Query only the user's indexed Zotero library through the deep-zotero MCP server, which provides semantic and exact-word search over pre-indexed PDF chunks, and citation graph data from OpenAlex. Synthesise the retrieved passages into bounded, claim-centred evidence cards so the caller does not need to ingest the full embedded-file context.
Never use model memory as evidence. Never search the web, start a browser, fetch a source, call the Zotero write API, or import an item or PDF. When the indexed corpus is insufficient, return a corpus-gap report to the caller and let the caller decide what to do about it.
Only a verbatim passage, table, or figure content retrieved from an indexed item can support a claim.
MCP Tools Available
All tools are provided by the deep-zotero MCP server:
Search
| Tool | Purpose |
|---|---|
search_papers |
Passage-level search over text, tables and figures. Returns chunks with surrounding context, metadata, relevance_score, and composite_score. Every result names its chunk_type. |
search_topic |
Find N most relevant papers for a topic, deduplicated by document. Returns per-paper average/best composite scores, best passage, and citation key. |
search_papers covers all three content types; narrow with chunk_types=["text"], ["table"] or ["figure"].
A table result carries its markdown in passage plus table_index, caption, num_rows and num_cols. A figure result carries its caption in passage plus figure_index, caption and image_path, the extracted PNG.
Exact Word Matching
search_papers takes required_terms: words that must appear in the passage as whole words, case-insensitively. terms_operator is "AND" (default) or "OR". No stemming, no phrase search.
Terms constrain the search itself, so a passage containing a rare acronym is found even when semantic similarity would not rank it. Omit query to retrieve every matching passage, unranked, with no embedding call. At least one of query or required_terms is required.
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.
- 12d ago First seen · 472 lines · 77 tokens per session scan A 9b05656657af
zotero-research is a skill published in the GitHub repository ccam80/deep-zotero (9 stars, last pushed 5d ago), licensed MIT. It adds 77 tokens to every session and 5,957 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…