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/light-zju/research-toolkit/paper-readernpx skills add Light-zju/research-toolkit --skill paper-readergit clone --depth 1 https://github.com/Light-zju/research-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/light-zju/research-toolkit/paper-reader)<a href="https://agentmods.dev/skills/light-zju/research-toolkit/paper-reader"><img src="https://agentmods.dev/badge/skills/light-zju/research-toolkit/paper-reader.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 | $0.00075 | $0.00437 |
| Opus 5 | $0.00037 | $0.00218 |
| Sonnet 5 | $0.00015 | $0.00087 |
| Haiku 4.5 | $0.00007 | $0.00044 |
Grade A, and why
paper-reader 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 5d 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.
What it actually says
Read before execution:
../references/research-principles.md ../references/evidence-policy.md ../references/search-policy.md ../references/failure-handling.md
Load domain-expansions.md when required.
Paper Reader
Purpose:
Help users understand a paper efficiently.
Focus on understanding rather than evaluation.
Scope
Primary:
- understanding
- explanation
- interpretation
Secondary:
- brief assessment
- resource discovery
Not responsible for:
- detailed review
- implementation planning
- research proposal generation
Workflow
- Metadata
Extract:
- Title
- Authors
- Affiliation
- Venue
- Year
- DOI
- Code Repository
- Project Page
- Executive Summary
Answer:
- What problem is solved?
- Why does it matter?
- What is proposed?
- What are the key results?
- Problem & Motivation
Explain:
- research problem
- existing limitations
- motivation
- Method
Explain:
- inputs
- outputs
- pipeline
- key modules
- important equations
Focus on intuition before details.
- Experiments
Explain:
- datasets
- baselines
- metrics
- findings
Interpret results.
Do not merely repeat tables.
- Figures & Tables
For each figure/table:
- what it shows
- key observation
- significance
- Knowledge Graph
Build a structured concept hierarchy.
- Learning Roadmap
Provide:
- essential prerequisites
- recommended topics
- advanced topics
- Quick Assessment
Briefly identify:
- novelty
- limitations
- practical applications
Keep concise.
Do not perform full review.
Output Style
Use clear structure.
Use intuitive explanations.
Prefer understanding over technical jargon.
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.
- 5d ago First seen · 151 lines · 75 tokens per session scan A 21736e5db9e9
paper-reader is a skill published in the GitHub repository Light-zju/research-toolkit (5 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 437 once invoked, about $0.0004 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).