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.
git clone --depth 1 https://github.com/tuoxie2046/claude-code-research-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/plugins/tuoxie2046/claude-code-research-skills/nature-skills)<a href="https://agentmods.dev/plugins/tuoxie2046/claude-code-research-skills/nature-skills"><img src="https://agentmods.dev/badge/plugins/tuoxie2046/claude-code-research-skills/nature-skills/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/plugins/tuoxie2046/claude-code-research-skills/nature-skills"><img src="https://agentmods.dev/badge/plugins/tuoxie2046/claude-code-research-skills/nature-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
nature-skills 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 10 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 1,204 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill nature-reviewer A 96 tokens
- Skill nature-academic-search A 163 tokens
- Skill nature-citation A 150 tokens
- Skill nature-data A 90 tokens
- Skill nature-figure A 149 tokens
- Skill nature-paper2ppt A 146 tokens
- Skill nature-polishing A 136 tokens
- Skill nature-reader A 116 tokens
- Skill nature-writing A 67 tokens
- Skill nature-response A 91 tokens
- MCP server academic-search A not measured
What ships with it
1 file beside plugin.json 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.
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 · 14 lines scan A 006ecf9c6537
nature-skills is a plugin published in the GitHub repository tuoxie2046/claude-code-research-skills (5 stars, last pushed 4mo ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
academic-skills-food-nutrition
Original, MIT-licensed academic skills for food, nutrition & agricultural science: research, journal-aware writing, peer review, and end-to-end orchestration, plus publisher-tiered journal author-guideline skills (food, nutrition, agriculture Q1/Q2, and multidisciplinary) and a scientific figure workflow, for Claude…
aej-applied-economics-skills
Agent skill stack for manuscripts targeted at the American Economic Journal: Applied Economics (AEJ: Applied) — the American Economic Association's quarterly journal for empirical applied microeconomics with credible causal identification, spanning labor, development, health, education, public, urban, environmental…
aej-microeconomics-skills
Agent skill stack for manuscripts targeted at the American Economic Journal: Microeconomics (AEJ: Micro) — the American Economic Association's quarterly journal for microeconomic THEORY and its applications (game theory, mechanism and market design, industrial-organization theory, contract theory, information…
aistats-skills
A 12-skill depth pack for AISTATS submissions: topic fit, OpenReview submission checks, author discussion, camera-ready, artifacts, reproducibility, supplementary material, review process, writing style, related work, experiments, and workflow. Grounded in official AISTATS 2026 CFP, OpenReview group, PMLR proceedings…
thesis
The research lifecycle for a master's thesis or paper: research question and proposal, multi-source literature search, structured paper notes, a verified BibTeX bibliography, citation verification with a hook that catches invented keys as they are written, argument-first literature synthesis, research design and…
animating-computational-mechanics
Animate continuum mechanics, tensor calculus, and FEM concepts with Matplotlib, Manim, or Blender — pedagogical animations for lectures and papers. Distilled from Flaschel 2026 (Comp. Applic. in Engineering Education) plus the DrSimulate gallery.