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.
npx skills add X1AOX1A/ZoFiles --skill read-papergit clone --depth 1 https://github.com/X1AOX1A/ZoFilesWrote 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/x1aox1a/zofiles/read-paper)<a href="https://agentmods.dev/skills/x1aox1a/zofiles/read-paper"><img src="https://agentmods.dev/badge/skills/x1aox1a/zofiles/read-paper/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/x1aox1a/zofiles/read-paper"><img src="https://agentmods.dev/badge/skills/x1aox1a/zofiles/read-paper.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 | $0.00153 | $0.01454 |
| Opus 5 | $0.00077 | $0.00727 |
| Sonnet 5 | $0.00031 | $0.00291 |
| Haiku 4.5 | $0.00015 | $0.00145 |
Grade B, and why
read-paper scanned grade B with 1 finding 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**Not all files may be present.** If a file is missing (e.g. no `kimi.md` or `paper.md`), skip it gracefully and work with what's available. Never tell the user a file "should" exist — just use alternative sources. For e How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading Paper Folders
Paper folders are exported by ZoFiles from Zotero. Each folder is named {arxivId} - {title} and contains structured files about one academic paper.
Paper Library Location
The paper library is at:
<FILL_IN: ask the user for their ZoFiles export root path, then update this file>
First-use setup: If the path above says
<FILL_IN...>or doesn't exist, ask the user: "What's the path to your ZoFiles paper library?" Then:
- Update the path above
- Run
scan-library.shto populate the directory snapshot (see Updating the Directory Snapshot)
Directory Structure
The library mirrors Zotero's collection hierarchy. Collections become directories, sub-collections become subdirectories, and paper folders sit at the leaves.
Key patterns:
Allin/directories appear when a collection has subcollections — contains all papers from that collection and every descendant (flat view of the entire subtree).- Paper folders are named
{arxivId} - {title}(e.g.2512.18832 - From Word to World...). - Find by arXiv ID: glob
**/2512.18832*from the library root. - Browse a topic: list the corresponding collection directory.
- See all papers: glob
**/paper.mdor**/arxiv.idrecursively.
Current Library Snapshot
<FILL_IN: run the scan script below to populate this snapshot>
Use this snapshot to quickly orient yourself when the user asks about topics, collections, or paper counts — no need to scan the filesystem each time.
Updating the Directory Snapshot
When the user asks to update the directory structure (e.g. "更新目录", "update directory", "refresh library"):
bash .claude/skills/read-paper/scripts/scan-library.sh "<library_root>"
Then replace the content between <!-- AUTO-GENERATED --> and <!-- END AUTO-GENERATED --> markers in this file with the new output (wrapped in a ```code block), and update the<!-- Last updated: ... --> date.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 119 lines · 153 tokens per session scan B dc4624ddaf3e
read-paper is a skill published in the GitHub repository X1AOX1A/ZoFiles (31 stars, last pushed 3mo ago), licensed MIT. It adds 153 tokens to every session and 1,454 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
bioservices
Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use…
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
cellxgene-census
Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…
dnanexus-integration
DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.