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
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.
git clone --depth 1 https://github.com/Galaxy-Dawn/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/analyze-results)<a href="https://agentmods.dev/commands/galaxy-dawn/claude-scholar/analyze-results"><img src="https://agentmods.dev/badge/commands/galaxy-dawn/claude-scholar/analyze-results/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/analyze-results"><img src="https://agentmods.dev/badge/commands/galaxy-dawn/claude-scholar/analyze-results.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 | $0.00000 | $0.01918 |
| Opus 5 | $0.00000 | $0.00959 |
| Sonnet 5 | $0.00000 | $0.00384 |
| Haiku 4.5 | $0.00000 | $0.00192 |
Grade A, and why
analyze-results 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Results Command
执行 blocker-first 实验后分析 + 报告工作流。
这是用户默认应该使用的入口，但它不是无条件“一键成稿”。它必须先判断证据是否足够，再决定进入 strict analysis、read-only audit、figure generation 或 results report。
如果你只是想“跑严格统计和科研图，不写总结报告”，才单独走 results-analysis。
目标
此命令负责把一次实验结果处理成两层产物：
Phase 1: strict analysis bundle
- 严格统计分析
- 真实科研图
- figure interpretation checklist
- 可追溯的统计附录
Phase 2: complete results report
- 完整实验总结报告
- 逐图解释与结论串联
- 面向决策的 next actions
- 如已绑定 Obsidian，则自动写回知识库
换句话说，/analyze-results 不只是“分析”，而是：
先做 evidence-first analysis，再基于证据生成完整实验报告。
默认编排
命令默认按以下顺序执行：
- Blocker-first gate
- 锁定 primary question、primary metric、unit of analysis、seed/run/fold/subject 数、raw provenance、comparison family
- 如果现有 stats table 的 p-value、interpretation、test method、unit of analysis 或 comparison family 互相矛盾，先 quarantine 该统计文件
- 如果这些信息不足，先输出 blocker summary 或 read-only audit，不生成完整报告
- 定位输入
- 找到实验目录、CSV/JSON、日志、图表原料与比较对象
- Phase 1 严格分析
- 使用
results-analysis - 当用户要求 no-write / audit，或输入不足以生成分析产物时，只输出 valid/invalid statistics、claim candidates 和 blockers
- 使用
- Phase 2 完整报告
- 使用
results-report - 只在 Phase 1 产物包含
analysis-report.md、stats-appendix.md、figure-catalog.md和必要 provenance 时生成完整实验总结报告
- 使用
- 知识库回写
- 如果当前 repo 已绑定 Obsidian project memory，则写回
Results/Reports/、相关Experiments/、Daily/和 project memory
- 如果当前 repo 已绑定 Obsidian project memory，则写回
- 显式报告 blocker
- 若统计输入不足、无法画图或命名信息缺失，必须说明阻塞点，不能伪造结论
使用方法
基本用法
/analyze-results
指定实验目录
/analyze-results path/to/experiment_dir
指定分析类型
/analyze-results path/to/results comparison
指定报告用途与轮次
/analyze-results path/to/results full transfer-summary 3 freezing
参数说明
| 参数 | 说明 |
|---|---|
data_path |
实验结果路径，可为目录、CSV、JSON 或日志 |
analysis_type |
full / comparison / ablation / visualization / audit |
purpose |
报告用途 slug；默认自动推断，无法推断时需显式说明 |
round |
实验轮次；用于报告命名，未知时允许暂用 r00 并注明 |
experiment_line |
实验线 slug，如 freezing、contrastive-adversarial |
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 · 202 lines · 0 tokens per session scan A 4894ae3c98ff
analyze-results is a command published in the GitHub repository Galaxy-Dawn/claude-scholar (5,431 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,918 tokens. 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
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.
causal-design
Design or audit the identification strategy for an observational study. Use when the task concerns estimands, causal assumptions, threats to identification, or defensible research design rather than model implementation.
cite-check
Verify that citations actually exist and that the claims they support are faithful to the cited source. Runs deterministic existence checks (Crossref / OpenAlex / Semantic Scholar / arXiv) plus a claim-faithfulness pass via the alterlab-citation-verifier skill.
brainstorm
Pre-implementation collaborative requirement exploration and design (conversational brainstorm).
SIMULATION_EXAMPLES
Inspired by "AI agents at their most under-leveraged point" by AI News & Strategy Daily | Nate B. Jones Source: https://www.youtube.com/watch?v=duA2AwL7keg.