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/mine-writing-patterns)<a href="https://agentmods.dev/commands/galaxy-dawn/claude-scholar/mine-writing-patterns"><img src="https://agentmods.dev/badge/commands/galaxy-dawn/claude-scholar/mine-writing-patterns/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/mine-writing-patterns"><img src="https://agentmods.dev/badge/commands/galaxy-dawn/claude-scholar/mine-writing-patterns.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 | $0.00042 | $0.00945 |
| Opus 5 | $0.00021 | $0.00473 |
| Sonnet 5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
mine-writing-patterns scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mine-writing-patterns - Installed Writing Memory Mining
Read the paper source "$source" and update the active installed paper-miner writing memory.
Default target
Always write mined knowledge into the active installed skill memory, not the repository checkout copy:
~/.claude/skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md
This command does not create project-specific writing memory unless the user explicitly asks for a project-local writing memory.
When to use
Use this command when you want to:
- learn reusable writing patterns from a strong paper,
- study how a venue frames introductions, methods, results, or rebuttals,
- mine phrasing and structure signals before drafting,
- enrich the writing memory that powers
ml-paper-writingandreview-response.
Usage
Basic usage
/mine-writing-patterns path/to/paper.pdf
Mine from an arXiv paper
/mine-writing-patterns https://arxiv.org/abs/2301.xxxxx
Focus on rebuttal or venue signals
/mine-writing-patterns path/to/paper.pdf rebuttal
/mine-writing-patterns path/to/paper.pdf venue
Workflow
Step 1: Resolve the paper source
Acceptable inputs:
- local PDF
- local DOCX
- arXiv URL
- readable web URL
- short natural-language request that identifies the paper(s)
If the source is ambiguous, narrow it before mining.
Step 2: Invoke paper-miner
Use the paper-miner agent to:
- extract paper content,
- identify reusable writing knowledge,
- merge it into the active installed writing memory,
- avoid duplicate entries,
- preserve source attribution.
Step 3: Respect the focus mode
Interpret $focus as follows:
| Focus | Priority |
|---|---|
general |
Mine balanced signals across all major sections |
introduction |
Emphasize framing, motivation, and contribution setup |
method |
Emphasize exposition style, technical sequencing, and clarity |
results |
Emphasize result narration, claim-evidence language, and interpretation |
rebuttal |
Emphasize clarification phrases, response structure, and reviewer-facing tone |
venue |
Emphasize venue-specific style and convention signals |
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 · 136 lines · 42 tokens per session scan A adaadf7ffef1
mine-writing-patterns is a command published in the GitHub repository Galaxy-Dawn/claude-scholar (5,407 stars, last pushed 13d ago), licensed MIT. It adds 42 tokens to every session and 945 once invoked, about $0.0002 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
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.
fix
User-triggered workflow to automatically fix open issues.
brainstorm
Pre-implementation collaborative requirement exploration and design (conversational brainstorm).