What is coarse-ink-claude-code CLAUDE.md?

Project instructions for a workspace that reviews academic papers from PDF files using the Coarse protocol. They describe where to place papers, where reviews are saved, and which helper scripts support the process.

Use them to request a review of a paper, extract and structure PDF text, verify quotations, and manage the review workspace.

They provide a repeatable way to run reviews and explain the files and Python setup the workspace expects.

How Felipe-SO/coarse-ink-claude-code configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Felipe-SO/coarse-ink-claude-code. 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/Felipe-SO/coarse-ink-claude-code/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Felipe-SO/coarse-ink-claude-code

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/felipe-so/coarse-ink-claude-code/claude-md/github.svg)](https://agentmods.dev/instructions/felipe-so/coarse-ink-claude-code/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/felipe-so/coarse-ink-claude-code/claude-md"><img src="https://agentmods.dev/badge/instructions/felipe-so/coarse-ink-claude-code/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/felipe-so/coarse-ink-claude-code/claude-md"><img src="https://agentmods.dev/badge/instructions/felipe-so/coarse-ink-claude-code/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,709 This file is loaded in full into every session.

When invoked 2,709 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.

Model	Per session	Once invoked
Fable 5.1	$0.02709	$0.02709
Opus 5.5	$0.01084	$0.01084
Sonnet 5.5	$0.00542	$0.00542
Haiku 4.5	$0.00271	$0.00271

Measured 2mo ago against content hash 6ef7c7fbd626, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coarse-ink-claude-code 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 2mo 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 · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Review Workspace

This folder is a workspace for reviewing academic papers using the Coarse protocol. Drop a PDF into papers/, ask for a review, and the output is saved to reviews/.

Layout

papers/                ← place PDFs here before requesting a review
reviews/               ← completed review markdown files saved here
reference_review.md    ← gold standard example review (economics/RD paper)
scripts/               ← Python helper scripts (extract, structure parse, quote verify)
.claude/skills/        ← coarse-review skill definition
.coarse_cache/         ← intermediate files per review (gitignore this)
src/coarse/            ← coarse Python package

How to request a review

Invoke the skill: /coarse-review papers/paper-name.pdf

Or just say: "Review papers/paper-name.pdf" — Claude Code will invoke the skill automatically.

Python environment (workspace scripts)

Install once: uv pip install -e . Then run scripts directly: python scripts/coarse_extract.py ...

If OPENROUTER_API_KEY is set, extraction uses Mistral OCR. Without it, extraction falls back to pymupdf (free, no key needed).

Output format

Reviews must match this exact structure (refine.ink format):

# Paper Title

**Date**: MM/DD/YYYY
**Domain**: social_sciences/economics
**Taxonomy**: academic/research_paper
**Filter**: Active comments

---

## Overall Feedback

Here are some overall reactions to the document.

[Optional 2-3 sentence assessment of the paper's contribution and what it does well]

**Issue Title**

Issue body paragraph (4-8 sentences: what is wrong, why it matters, specific fix).

[More issues...]

**Recommendation**: accept | minor revision | major revision | reject — 2-3 sentence justification.

**Key revision targets**:
1. Specific actionable target
2. ...

**Status**: [Pending]

---

## Detailed Comments (N)

### 1. Comment title

**Status**: [Pending]

**Quote**:
> Exact verbatim text from the paper (multi-line: prefix each line with "> ")

**Feedback**:
Explanation of the issue with a specific fix.

---

Read the full file on GitHub · 251 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.

2mo ago First seen · 251 lines · 2,709 tokens per session scan A 6ef7c7fbd626

Subscribe to this mod's changes

coarse-ink-claude-code CLAUDE.md is an instructions file published in the GitHub repository Felipe-SO/coarse-ink-claude-code (2 stars, last pushed 6mo ago), licensed MIT. It adds 2,709 tokens to every session, about $0.0108 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 2026-08-31.

Documents PDF Research

coarse-ink-claude-code CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
coarse-ink-claude-code CLAUDE.mdFelipe-SO/coarse-ink-claude-code	Instructions file	2	6mo ago	MIT	A	2,709	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

coarse-ink-claude-code: Instructions file for Claude Code