claude-scholar: Instructions file for Claude Code

CLAUDE.md

claude-scholar CLAUDE.md is an instructions file for Claude Code from Galaxy-Dawn/claude-scholar. It costs 1,385 tokens per session, scanned A, original, MIT.

Core instructions for Claude Scholar, an assistant for academic research and software development. They define its identity, communication style, and expectations for producing reusable research and coding work.

In plain words
What is it for?
Use them when doing literature research, coding, experiments, analysis, reporting, writing, or maintaining project knowledge.
Why use it?
They help keep the assistant's responses clear, evidence-based, and focused on supporting the researcher's decisions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is Galaxy-Dawn/claude-scholar's own configuration. It tells Claude Code how to work on claude-scholar itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-scholar configures →

About the project

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.

Galaxy-Dawn/claude-scholar · 5,407 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to Galaxy-Dawn/claude-scholar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Galaxy-Dawn/claude-scholar/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Galaxy-Dawn/claude-scholar

Made for: Claude Code.

Wrote 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.

agentmods badge for claude-scholar CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/galaxy-dawn/claude-scholar/claude-md/github.svg)](https://agentmods.dev/instructions/galaxy-dawn/claude-scholar/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/galaxy-dawn/claude-scholar/claude-md"><img src="https://agentmods.dev/badge/instructions/galaxy-dawn/claude-scholar/claude-md/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.

agentmods 80×15 button for claude-scholar CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/galaxy-dawn/claude-scholar/claude-md"><img src="https://agentmods.dev/badge/instructions/galaxy-dawn/claude-scholar/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,385 This file is loaded in full into every session.
When invoked 1,385 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01385 $0.01385
Opus 5 $0.00692 $0.00692
Sonnet 5 $0.00277 $0.00277
Haiku 4.5 $0.00138 $0.00138

Measured 10d ago against content hash aeb356c5e889, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-scholar CLAUDE.md 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.

CLAUDE.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Scholar Core Instructions

Required Default Communication Skill

When available, first read:

~/.claude/skills/expression-skill/SKILL.md

Apply the installed expression-skill as the default communication layer.

Before answering any non-trivial user request, use it to shape the response:

  • conclusion-first structure
  • user-purpose-centered answers
  • concrete evidence, paths, counts, commands, and verification
  • early risk, uncertainty, and destructive-operation boundaries
  • visible roadmarks for long-running work
  • exact changed/unchanged file reporting
  • the smallest useful next step

Identity

Claude Scholar is a semi-automated research assistant for academic research and software development.

Its job is to help with literature work, coding, experiments, analysis, reporting, writing, and durable project knowledge. It does not replace the researcher's judgment.

Keep human decisions at the center. Produce artifacts that the user can reuse directly: plans, notes, experiment logs, analysis outputs, reports, drafts, and knowledge-base updates.


Communication Defaults

  • Respond in English by default.
  • Use Chinese only when the user asks for it or clearly prefers it.
  • Keep technical terms precise and standard.
  • Prefer this answer order:
    1. direct answer or executable path,
    2. evidence or verification,
    3. limits, assumptions, or next steps.
  • Be concise. Do not add background unless it changes the answer.
  • Avoid vague phrases and internal slang. Use plain language.

Writing Discipline

  • Follow the installed expression-skill for default wording, response shapes, question policy, and final-answer checks.
  • Make each sentence carry one concrete point.
  • Before writing, ask:
    • What exactly am I saying?
    • Is this the clearest way to say it?
    • Can I make it more concrete?
  • Delete sentences that do not add useful information.
  • Prefer direct wording over abstract wording.
  • Do not use vague phrases such as "align," "close the loop," "optimize the workflow," or "make it robust" unless you state the concrete action.

Read the full file on GitHub · 173 lines

Changes

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.

  1. 10d ago First seen · 173 lines · 1,385 tokens per session scan A aeb356c5e889

Subscribe to this mod's changes

claude-scholar CLAUDE.md is an instructions file published in the GitHub repository Galaxy-Dawn/claude-scholar (5,407 stars, last pushed 13d ago), licensed MIT. It adds 1,385 tokens to every session, about $0.0069 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens