Claude Scholar is a semi-automated research assistant for academic research and software development, supporting literature review, coding, experiments, reporting, writing, and project knowledge management. Computer science and AI researchers use it across the research workflow with several coding-agent platforms; the catalogue contains its skills, commands, agents, hooks, plugin, and instruction.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Galaxy-Dawn/claude-scholar/plugin install claude-scholarWrote 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/commands/galaxy-dawn/claude-scholar/zotero-notes)<a href="https://agentmods.dev/commands/galaxy-dawn/claude-scholar/zotero-notes"><img src="https://agentmods.dev/badge/commands/galaxy-dawn/claude-scholar/zotero-notes/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/commands/galaxy-dawn/claude-scholar/zotero-notes"><img src="https://agentmods.dev/badge/commands/galaxy-dawn/claude-scholar/zotero-notes.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 | $0.00029 | $0.01307 |
| Opus 5 | $0.00015 | $0.00654 |
| Sonnet 5 | $0.00006 | $0.00261 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
zotero-notes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/zotero-notes - Zotero to Obsidian Reading Notes
Read papers from the Zotero collection "$collection" and create or update detailed reading notes.
Default target
- Preferred target: the bound Obsidian project knowledge base (
Sources/Papers/*.md) - Fallback target:
reading-notes-{collection}.mdin the working directory if the current repo is not bound to Obsidian
Workflow
Step 0: Resolve whether the current repo is Obsidian-bound
- If
.claude/project-memory/registry.yamlexists for the current repo, treat the bound vault as the primary output target. - If the repo is a research project but not yet bound, bootstrap it first.
- If there is no bound project context, fall back to a plain markdown output in the working directory.
- Treat this command as an explicit agent-first ingestion pass under
$zotero-obsidian-bridge.
Step 1: Load papers from Zotero
- Call
mcp__zotero__zotero_get_collectionsto find the matching collection. - Call
mcp__zotero__zotero_get_collection_itemsto list the papers. - For each item, call:
mcp__zotero__zotero_get_item_metadatamcp__zotero__zotero_get_item_fulltextwhen a PDF is availablemcp__zotero__zotero_get_annotationswhen helpfulmcp__zotero__zotero_get_noteswhen helpful
- If MCP transport fails but a local
zotero-mcpcheckout is available, use the local Python fallback instead of stopping the pass. - Treat Zotero
webpageitems as weak-source inputs unless they clearly expose full paper metadata and useful full text. Abstract-only or placeholder pages must stayTo-Readand cannot supportKnowledgeorWritingclaims.
Step 2: Create/update the canonical paper note
If the project is Obsidian-bound, create or update one canonical note per paper under Sources/Papers/.
Each detailed note should contain:
ClaimResearch questionMethodEvidenceStrengthsLimitationDirect relevance to repoRelation to other papersKnowledge linksOptional downstream hooks- canonical
Evidence RecordwithSource typeandClaim strengthwhen the paper has reusable claims
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.
- 10d ago First seen · 129 lines · 29 tokens per session scan A 77dfbc590e0f
zotero-notes is a command published in the GitHub repository Galaxy-Dawn/claude-scholar (5,407 stars, last pushed 13d ago), licensed MIT. It adds 29 tokens to every session and 1,307 once invoked, about $0.0001 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 commands, from other repositories
zotero-notes
Batch read papers from Zotero collection and generate structured reading notes for each paper.
rb-ask
A command for asking questions about the current codebase through RepoBrain, a code knowledge tool.
rb-refresh
A command that rebuilds RepoBrain's knowledge base for the current workspace. RepoBrain is a tool that keeps searchable project information for an agent.
pr-review
Generate a PR review report aggregating quality scan, coverage, complexity, and breaking changes.
task
Start TASK phase — task decomposition.
brainstorm
Pre-implementation collaborative requirement exploration and design (conversational brainstorm).