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 agentmods add skills/sjqsgg/paperwise/paperwisenpx skills add sjqsgg/Paperwise --skill paperwisegit clone --depth 1 https://github.com/sjqsgg/PaperwiseWrote 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/sjqsgg/paperwise/paperwise)<a href="https://agentmods.dev/skills/sjqsgg/paperwise/paperwise"><img src="https://agentmods.dev/badge/skills/sjqsgg/paperwise/paperwise.svg" alt="Measured on agentmods" 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 | $0.04527 |
| Opus 5 | $0.00021 | $0.02263 |
| Sonnet 5 | $0.00008 | $0.00905 |
| Haiku 4.5 | $0.00004 | $0.00453 |
Grade A, and why
paper 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 6d 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/paper — Academic Paper Workflow
Default Config
Edit this section to customize for your project.
output_dir: "./papers"
# Obsidian vault users: set paper_output_dir in your project's CLAUDE.md
# Drive/OneDrive: use the appropriate MCP, then set path (e.g. "gdrive://My Drive/Papers")
venues: [CHI, ACL, EMNLP, NAACL, NeurIPS, ICML, ICLR, EDM, LAK, AIED, ITS, CSCW, SIGIR, CIKM]
keywords:
- cognitive load
- adaptive learning
- intelligent tutoring
- conversational learning
- LLM tutoring
- learning analytics
- behavioral signals
- educational dialogue
min_citations: 5 # /paper find: filter out papers with fewer citations
daily_max: 10 # /paper digest: max papers per run
annotation_lang: zh # zh = Chinese annotations | en = English; override with --lang
openalex_email: "" # Optional. Add email to join OpenAlex Polite Pool (higher rate limits).
semantic_scholar_api_key: "" # Optional. Free key: semanticscholar.org/product/api
Override any config value in your project's CLAUDE.md using keys: paper_output_dir, paper_venues, paper_keywords, paper_annotation_lang.
Subcommands
| Command | Usage | Description |
|---|---|---|
find |
/paper find "cognitive load LLM" |
Search papers → Digest HTML with top N cards |
read |
/paper read /path/to/file.pdf |
Annotate a single PDF → full dual-column HTML |
digest |
/paper digest |
Daily new papers from arxiv (used by cron) |
cite |
/paper cite [[note-name]] |
Generate APA + BibTeX citation from existing annotation |
Flags:
--context "ML课第3周"— override project context--questions "Q1:... Q2:..."— switch to Question mode (Mode A)--questions— interactive question mode (Claude asks you)--output /path/— override output directory for this run--top N— return N results (default: 5 for find, daily_max for digest); also accepts bare number after query--lang en— override annotation language for this run--source arxiv— search only arxiv (latest preprints, no citation filter)--source venues— search only papers from configvenueslist (citation-weighted ranking)--local /path/— read local PDFs from folder (no API calls); or--local a.pdf b.pdffor specific files
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.
- 6d ago First seen · 378 lines · 42 tokens per session scan A 0446675368a4
paper is a skill published in the GitHub repository sjqsgg/Paperwise (135 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 4,527 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 skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…