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 adolinjonathan-bot/zotero-toolkit --skill research-assistantgit clone --depth 1 https://github.com/adolinjonathan-bot/zotero-toolkitWrote 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/adolinjonathan-bot/zotero-toolkit/research-assistant)<a href="https://agentmods.dev/skills/adolinjonathan-bot/zotero-toolkit/research-assistant"><img src="https://agentmods.dev/badge/skills/adolinjonathan-bot/zotero-toolkit/research-assistant/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/adolinjonathan-bot/zotero-toolkit/research-assistant"><img src="https://agentmods.dev/badge/skills/adolinjonathan-bot/zotero-toolkit/research-assistant.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 | $0.00035 | $0.00855 |
| Opus 5.5 | $0.00014 | $0.00342 |
| Sonnet 5.5 | $0.00007 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
research-assistant 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 today.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Assistant Skill
Use this skill for day-to-day research tasks over a Zotero library: answering literature questions, finding relevant references, checking claims against full text, filing new references with valid schemas, and generating formatted citations and bibliographies.
Core Principles
- Choose the right search mode (
qmode).- Use
qmode="titleCreatorYear"when looking for a specific author, title keyword, or core topic. - Use
qmode="everything"(the default) when searching for concepts, methods, or quotes that may appear inside attached PDFs.
- Use
- Use boolean filters to narrow results.
item_type="-attachment"excludes standalone files.item_type="journalArticle || conferencePaper"matches either type.tag="-Read"finds items not yet taggedRead.- Always check exact tag spelling with
zotero_list_tagsbefore filtering by tag.
- Ground every literature claim in a Zotero item key. Cite both the author-year and
[key: ABCD1234]during drafting so every statement traces to a specific record in the library, then render final citations withzotero_get_citations. - Check schema before creating unfamiliar item types. Call
zotero_get_item_type_schema(item_type=...)before callingzotero_create_itemon types likereport,thesis,presentation, orstatuteso Zotero does not reject invalid field names.
Common Workflows
1. Answering a Research Question from the Library
- Search broadly, then precisely: Run
zotero_search_itemswith targeted keywords anditem_type="-attachment". If results are noisy, switch toqmode="titleCreatorYear". - Batch-read metadata: Use
zotero_get_itemsto inspect abstracts and metadata for the top candidates in a single request. - Verify against full text: For the most relevant papers, call
zotero_get_item_fulltextto verify methods, sample details, and exact claims rather than relying solely on abstracts. - Synthesize with citations: Group findings thematically, noting agreements, contradictions, and gaps across studies, and call
zotero_get_citations(style="apa","vancouver","harvard-cite-them-right", etc.) to append a properly formatted reference list.
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.
- today First seen · 50 lines · 35 tokens per session scan A 85150293f272
research-assistant is a skill published in the GitHub repository adolinjonathan-bot/zotero-toolkit (1 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 855 once invoked, about $0.0001 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 2026-10-24.
Other skills, from other repositories
research-manager
Use this when starting a new research project or managing a complex, multi-step research workflow.
academic-writing
You must use this when producing any research prose — literature reviews, syntheses, analyses, methodology descriptions, discussion sections, abstracts, or any written output intended for an academic audience.
systematic-review
You must use this when conducting PRISMA-standard systematic reviews, protocol development, or Risk of Bias assessment.
hypothesis-testing
You must use this when formulating testable hypotheses, designing experimental controls, or defining falsification criteria.
peer-review
You must use this when critiquing academic manuscripts, evaluating methodological rigor, or providing structured reviewer feedback.
research-methodology
You must use this when matching research questions to appropriate designs, sampling strategies, or validity controls — or when a research problem is stuck and needs creative reframing (cross-domain analogies, first-principles deconstruction).