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 Immortalqx/my_codex_skills --skill paper-readinggit clone --depth 1 https://github.com/Immortalqx/my_codex_skillsWrote 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/immortalqx/my_codex_skills/paper-reading)<a href="https://agentmods.dev/skills/immortalqx/my_codex_skills/paper-reading"><img src="https://agentmods.dev/badge/skills/immortalqx/my_codex_skills/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/immortalqx/my_codex_skills/paper-reading"><img src="https://agentmods.dev/badge/skills/immortalqx/my_codex_skills/paper-reading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 46 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00207 | $0.03525 |
| Opus 5 | $0.00103 | $0.01762 |
| Sonnet 5 | $0.00041 | $0.00705 |
| Haiku 4.5 | $0.00021 | $0.00352 |
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 10d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Reading
Paper request: $ARGUMENTS
This skill produces a deep, critical, structured reading note for a single research paper. The note follows a fixed 9-section template, embeds cropped figures from the paper, cites every claim with a numbered reference, and links only to external sources. The final note is written in the same language the user used to invoke the skill unless the user explicitly asks for another language.
Core Boundary
This skill is a personal reading note tool, not a peer review, not a survey, not a quick lookup.
Rules:
- Read the whole paper, including appendices. A skim of abstract plus experiments is not a reading.
- Be objective and critical. Quote the paper, do not advertise it. Words like "groundbreaking", "novel", "amazing", "revolutionary" require verifiable evidence and are usually wrong.
- Every claim must be traceable: cite the section, figure, or table. Every cited paper must have been re-fetched and read in original, not relied on from a secondary summary.
- Crop figures, do not paste whole pages. A figure that occupies half a page and is mostly whitespace or another figure is not informative. Crop further to the region that carries the argument.
- Numbered citations
[1],[2], etc. The reference list at the end of the note contains only external links (arXiv, DOI, publisher page). No local file paths in the reference list. - All downloaded papers live in the project that triggered the skill, never inside this skill's folder. The skill folder is meant to be reusable across projects.
- The final note is in the user's language. Chinese question -> Chinese note. English question -> English note. Explicit specification -> that specification.
Required Resources
Read these bundled files in this order, before drafting the final note:
references/note-template.md- 9-section reading note structurereferences/benchmark-guard.md- how to verify that each benchmark actually tests what the paper claimsreferences/related-work-schema.md- columns to use inrelated_work_matrix.mdreferences/critical-reading-checklist.md- objective and critical reading rulesreferences/output-contract.md- non-negotiable output rules: citation style, figure policy, anti-patterns, self-check
What ships with it
10 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.
- agents/openai.yaml 226 B
- references/benchmark-guard.md 6.6 KB
- references/critical-reading-checklist.md 5.5 KB
- references/note-template.md 7.6 KB
- references/output-contract.md 6.2 KB
- references/related-work-schema.md 4.2 KB
- scripts/extract_text.py 6.5 KB runs code
- scripts/locate_figures.py 12 KB runs code
- scripts/render_pages.py 9.3 KB runs code
- scripts/split_sections.py 7.8 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.
- 10d ago First seen · 184 lines · 207 tokens per session scan A fd29a7aea264
paper-reading is a skill published in the GitHub repository Immortalqx/my_codex_skills (52 stars, last pushed 1mo ago), licensed MIT. It adds 207 tokens to every session and 3,525 once invoked, about $0.0010 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
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
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.