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.
curl -O https://raw.githubusercontent.com/Felipe-SO/coarse-ink-claude-code/main/.claude/skills/coarse-review/SKILL.mdgit clone --depth 1 https://github.com/Felipe-SO/coarse-ink-claude-codeWrote 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/skills/felipe-so/coarse-ink-claude-code/coarse-review)<a href="https://agentmods.dev/skills/felipe-so/coarse-ink-claude-code/coarse-review"><img src="https://agentmods.dev/badge/skills/felipe-so/coarse-ink-claude-code/coarse-review/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/skills/felipe-so/coarse-ink-claude-code/coarse-review"><img src="https://agentmods.dev/badge/skills/felipe-so/coarse-ink-claude-code/coarse-review.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 | $0.00034 | $0.00604 |
| Opus 5 | $0.00017 | $0.00302 |
| Sonnet 5 | $0.00007 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
coarse-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/coarse-review — Full Review Pipeline
Usage: /coarse-review papers/paper.pdf
Runs the complete Coarse review pipeline by invoking each sub-skill in sequence.
All paths are relative to the workspace root d:/Dropbox/Research/Coarse Reviewer/.
The argument ($ARGUMENTS) is the path to the paper PDF.
Derive the slug from the filename: lowercase, spaces→hyphens, no extension.
e.g. papers/my-paper.pdf → slug = my-paper
Pass the PDF path only to coarse-extract. Pass the slug to all subsequent
sub-skills — they work entirely from cache files and never need the PDF again.
Pipeline
Run each sub-skill in order. Wait for each to complete before starting the next. If a sub-skill fails, stop and report the error — do not skip ahead.
| Step | Sub-skill | What it does | Output |
|---|---|---|---|
| 1–2 | /coarse-extract $ARGUMENTS |
PDF → markdown, parse sections | _extracted.md, _sections.json |
| 3–6 | /coarse-classify <slug> |
Classify, calibrate, contributions, literature | _classification.json, _calibration.json, _contribution.json, _literature.txt |
| 7–8 | /coarse-overview <slug> |
Macro overview + assumption check + completeness | _overview.json |
| 9–11 | /coarse-section-review <slug> |
Per-section review + adversarial proof verify + cross-section + compile | _comments_draft.json |
| 12–13 | /coarse-editorial <slug> |
Editorial filter + quote verify (Python) | _comments_verified.json |
| 14 | /coarse-write <slug> |
Write final review markdown | reviews/<slug>-review.md |
Cache location
All intermediate files are written to .coarse_cache/<slug>_*.json and
.coarse_cache/<slug>_extracted.md. If a run is interrupted, you can resume
from any sub-skill without re-running earlier steps — the cache files persist.
Notes
- Each sub-skill re-reads its dependencies from cache at startup, so context compression between steps is safe.
- To re-run only part of the pipeline (e.g. redo the editorial filter after adjusting a comment), invoke the relevant sub-skill directly.
- See
reference_review.mdfor the gold-standard output format.
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.
- 9d ago First seen · 56 lines · 34 tokens per session scan A 6e83df7a5de5
coarse-review is a skill published in the GitHub repository Felipe-SO/coarse-ink-claude-code (2 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 604 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 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.