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 Mizoreww/awesome-claude-code-config --skill paper-readinggit clone --depth 1 https://github.com/Mizoreww/awesome-claude-code-configWrote 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/mizoreww/awesome-claude-code-config/paper-reading)<a href="https://agentmods.dev/skills/mizoreww/awesome-claude-code-config/paper-reading"><img src="https://agentmods.dev/badge/skills/mizoreww/awesome-claude-code-config/paper-reading/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/mizoreww/awesome-claude-code-config/paper-reading"><img src="https://agentmods.dev/badge/skills/mizoreww/awesome-claude-code-config/paper-reading.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 | $0.00100 | $0.02383 |
| Opus 5.5 | $0.00040 | $0.00953 |
| Sonnet 5.5 | $0.00020 | $0.00477 |
| Haiku 4.5 | $0.00010 | $0.00238 |
Grade A, and why
paper-reading 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 1mo 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper reading
Treat a paper report as an argument with inspectable evidence, not a longer abstract. Preserve the familiar paper-type structure and the original technical template while cutting any sentence that adds no mechanism, evidence, comparison, limitation, or implication.
Resolve <skill-dir> as the directory containing this file before using bundled scripts or assets.
In examples, PYTHON_EXE means the actual interpreter of a compatible active or isolated environment—for example python3, python, py -3, or an absolute venv executable. Resolve it for the current platform; do not run the token literally or assume one command name exists.
1. Choose only the output format
Honor an explicit or clearly implied format. Otherwise ask once whether the user wants Markdown or HTML, then wait. Explain briefly: Markdown is light and editable; HTML adds the designed reading surface, one section outline, static mathematics, and click-to-enlarge visuals.
Do not ask for a reading level. Use one standard throughout: read the complete argument, retain all load-bearing technical detail, and write it concisely. Do not run reproduction experiments as part of this workflow.
Gate: record format; do not silently choose it when genuinely ambiguous.
2. Ground the source
Accept a local or remote PDF, official full-text HTML, or complete pasted text. Prefer PDF when available because page and figure anchors are stable; do not make PDF mandatory.
For a PDF, keep the source unchanged and extract into a new directory:
uv run --isolated --no-project --with pymupdf4llm==1.28.0 \
python <skill-dir>/scripts/extract_paper.py PAPER.pdf EXTRACTED_DIR
If uv is unavailable, use an isolated standard venv. Reuse an already-compatible environment when possible. Never require Conda or install into a base, system, or global environment.
The extractor writes page-anchored text, source hashes, and an immutable assets/raw/ manifest. Copy selected visuals into the report; never delete raw extraction to “clean” it.
What ships with it
17 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.
- assets/report-template.html 2.0 KB
- assets/report.css 14 KB
- assets/report.js 8.8 KB runs code
- references/code-audit.md 3.0 KB
- references/empirical.md 4.1 KB
- references/evidence.md 4.6 KB
- references/html-report.md 15 KB
- references/shared-sections.md 3.8 KB
- references/survey.md 1.6 KB
- references/systems.md 2.1 KB
- references/theoretical.md 1.5 KB
- references/visuals.md 5.2 KB
- scripts/extract_paper.py 13 KB runs code
- scripts/mathml_policy.py 3.7 KB runs code
- scripts/render_math.py 9.0 KB runs code
- scripts/scaffold_report.py 21 KB runs code
- scripts/validate_report.py 42 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.
- 1mo ago First seen · 127 lines · 100 tokens per session scan A e04f3ec16b2d
paper-reading is a skill published in the GitHub repository Mizoreww/awesome-claude-code-config (259 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 2,383 once invoked, about $0.0004 per session on Opus 5.5. 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
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…