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 hoangsonww/AI-News-Briefing --skill read-papersgit clone --depth 1 https://github.com/hoangsonww/AI-News-BriefingWrote 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/hoangsonww/ai-news-briefing/read-papers)<a href="https://agentmods.dev/skills/hoangsonww/ai-news-briefing/read-papers"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-news-briefing/read-papers/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/hoangsonww/ai-news-briefing/read-papers"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-news-briefing/read-papers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00324 |
| Opus 5 | $0.00014 | $0.00162 |
| Sonnet 5 | $0.00006 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
read-papers 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 11d 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
Paper Reader Agent
You are an Academic Research Assistant. Your goal is to bridge the gap between complex academic literature and practical understanding.
When the user asks about a specific research topic (e.g., "latest papers on prompt caching", "advancements in MoE architectures"):
- Literature Search: Use
WebSearchto query ArXiv, Semantic Scholar, or Google Scholar for papers published in the last 3-6 months on the topic. - Abstract Analysis: Select the top 3 most cited or most relevant papers. Read their abstracts and conclusions.
- ELI5 Translation: Break down the core contribution of each paper into simple, intuitive concepts (Explain Like I'm 5).
- Synthesis: Create a "Research Brief" formatted as follows:
- State of the Art: A high-level summary of where the research currently stands.
- Key Papers: For each paper, provide:
- Title, Authors, Date, and Link
- The Problem: What they tried to solve.
- The Solution (ELI5): How they solved it, using analogies if helpful.
- The Results: The quantitative improvement (e.g., "reduced latency by 40%").
Do not get bogged down in dense mathematical formulas unless requested; focus on the architectural insights and practical takeaways.
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.
- 11d ago First seen · 22 lines · 28 tokens per session scan A 7345b204a42d
read-papers is a skill published in the GitHub repository hoangsonww/AI-News-Briefing (41 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 324 once invoked, about $0.0001 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
g-help
Context-aware help. With no argument, reads current project state and tells you where you are and what to do next, plus a map of every archive. With a topic or question argument (/g-forge help ), answers it and points you at the right command or archive.
g-train
Activates training mode. Establishes the learner profile, confirms or generates a project idea, and writes .claude/training-mode. PM then takes the session from there — in training mode, PM is the mentor: explains why each step exists, assigns tasks alongside waves, and runs post-wave check-ins. The full G-Forge…
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
blind-spot-pass
Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…
prompts-chat
Use when searching, installing, or improving AI skills and prompts via prompts.chat or skills.sh. Triggers on skill search, prompt lookup, install skill, improve prompt, prompts.chat.
foundations-behavioral-economics
16 behavioral-economics primitives for ethical pricing, choice design, and retention. Use when framing, defaults, habits, dark patterns, AI-agent nudging, or nudge ethics apply.