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/bahayonghang/my-ai-cli-toolkit/paper-workbenchnpx skills add bahayonghang/my-ai-cli-toolkit --skill paper-workbenchgit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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/bahayonghang/my-ai-cli-toolkit/paper-workbench)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/paper-workbench"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/paper-workbench.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 | $0.00102 | $0.01806 |
| Opus 5 | $0.00051 | $0.00903 |
| Sonnet 5 | $0.00020 | $0.00361 |
| Haiku 4.5 | $0.00010 | $0.00181 |
Grade A, and why
paper-workbench scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Write, WebFetch, Bash(curl *), Bash(python *), Bash(pytest *) How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Workbench
Unified entrypoint for paper intake, strategic reading, multi-paper synthesis, and review construction.
Keep paper-record as the normalization layer. Do not merge high-level
analysis back into the normalized record.
In the
pythoncommands below,<skill-dir>is this skill's base directory, announced when the skill loads. Substitute that literal path; it is not an environment variable. Bundled scripts self-locate, so only the path needs to resolve.
When to use
Use this skill when the job is to:
- read one paper quickly
- deeply deconstruct one paper
- compare or synthesize multiple papers
- build a review outline or gap map
- normalize paper sources into reusable machine-readable artifacts
Do not use this skill when the primary job is to implement a paper from its methods into working code. That implementation work is out of scope for this skill.
Public interfaces
paper-record— normalized single-paper factsresearcher-profile— user research anchorpaper-deep-read— single-paper strategic analysis artifactliterature-synthesis— cross-paper integration artifactreview-outline— literature-review planning artifact
Accepted inputs
- arXiv IDs and arXiv URLs
- AlphaXiv URLs
- DOI strings or
doi.org/...URLs - local academic PDFs or text files
- remote PDF URLs
- paper landing pages that expose a PDF
- existing
paper-recordJSON - existing
researcher-profile,paper-deep-read,literature-synthesis, orreview-outlineJSON
Routing workflow
- Resolve the input class from
$ARGUMENTS, the latest user message, or a pasted JSON artifact. - If the request is paper-level and not already normalized, run
scripts/normalize_paper.pyfirst. - Determine the mode from explicit user intent or the defaulting rules below.
- If the chosen mode is profile-sensitive, load the supplied
researcher-profileor collect only the missing fields. - Produce the requested mode output.
- Persist artifacts only when the user asked to save them.
What ships with it
23 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.
- evals/evals.json 3.5 KB
- references/ANALYSIS_FRAMEWORK.md 1.6 KB
- references/artifacts.md 2.7 KB
- references/migration.md 958 B
- references/modes/card.md 604 B
- references/modes/deep-read.md 1.1 KB
- references/modes/interpret.md 836 B
- references/modes/json.md 477 B
- references/modes/review.md 943 B
- references/modes/scan.md 560 B
- references/modes/synthesis.md 810 B
- references/modes/xray.md 1.0 KB
- references/routing.md 2.4 KB
- references/schema.md 1.7 KB
- references/template-paper.org 1.4 KB
- references/template-xray.org 1.2 KB
- scripts/normalize_paper.py 38 KB runs code
- scripts/workbench_io.py 7.8 KB runs code
- scripts/xray_io.py 4.0 KB runs code
- tests/fixtures/doctor_thesis.txt 605 B
- tests/fixtures/master_thesis.txt 590 B
- tests/fixtures/sample_local_paper.pdf 1.1 KB
- tests/test_normalize_paper.py 10 KB runs code
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 · 216 lines · 102 tokens per session scan A 15aeb60a4f7d
paper-workbench is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 1,806 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
academic-research
Nested swiss-knife reference for academic literature work — find papers, fetch full-text PDFs, trace citations, write LaTeX manuscripts. First action for any "get me this paper" request: python3 /scripts/fetchpaper.py — walks arXiv → Unpaywall → Europe PMC → CORE → in-house publisher-page extraction…
Deep Research
Produce a deep, structured research report on a topic: decompose into key dimensions, analyze each with evidence and reasoning, synthesize cross-cutting insights, and surface open questions. Use for deep research, analysis, and literature/landscape reviews.
scientific-writing
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting…
market-research-reports
Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework…
research-proposal
Generate academic research proposals for PhD applications. Use when user asks to "write a research proposal", "create PhD proposal", "generate research plan", "撰写研究计划", "写博士申请", "doctoral proposal", or mentions specific research topics for PhD application. Supports STEM, humanities, and social sciences with…
venue-templates
Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing…