Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add wenhaochai/claude-plugins/plugin install kexue-fmWrote 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/wenhaochai/claude-plugins/kexue)<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/kexue"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/kexue/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/wenhaochai/claude-plugins/kexue"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/kexue.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00099 | $0.00637 |
| Opus 5.5 | $0.00040 | $0.00255 |
| Sonnet 5.5 | $0.00020 | $0.00127 |
| Haiku 4.5 | $0.00010 | $0.00064 |
Grade A, and why
kexue scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
kexue
KX="${CLAUDE_PLUGIN_ROOT}/scripts/kexue.py"
DB="${CLAUDE_PLUGIN_ROOT}/data/kexue.sqlite"
python3 "$KX" search 查询1 查询2 ... [--since 2023-01-01] [--limit 20]
python3 "$KX" show ID
python3 "$KX" sync # 抓取新文章
也可以直接对 $DB 写 SQL：
posts(id, url, title, date, category, tags, readers, excerpt, content_md, cite_text, bibtex)，
fts(title, tags, content_md) 是 trigram 全文索引，rowid = posts.id。
查询思路
用户的问题往往和文中用词对不上。比如问「LLM 预训练」，文章里很少出现「预训练」，但会写 Muon、MuP、学习率、Batch Size、Scaling Law。所以不要只搜原词：
- 把问题拆成文中会出现的具体词，中英写法都试，一次传进去：
search 优化器 Muon MuP 学习率 "Batch Size" "Scaling Law" MoE 损失函数 --since 2023-01-01 - 每个参数是一路查询，结果按各路排名融合，
←后面标出命中了哪几路。命中路数多的文章更核心。 - 大问题按子主题分几次查，每次 8 到 12 路。优化器、学习率这类词命中面很广，和架构、分词类的词放在同一次里会把后者压到后面。
- 两个字的泛词（数据、模型、训练）不要单独成一路，会命中无关文章；和别的词合成一路加引号，如
"训练 数据"。 - 输出末尾列出无命中的查询，换同义词再搜。
- 对候选文章读
excerpt判断是否相关：sqlite3 "$DB" "select id, excerpt from posts where id in (...)"。 - 读正文用
show ID。长文可以用 SQL 取content_md的片段。回答时注明文章 id、标题和链接https://kexue.fm/archives/<id>，引用时给出cite_text或bibtex。
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.
- 14d ago Changed 72cc26bd6626
- 1mo ago First seen · 32 lines · 99 tokens per session scan A ae0868e3b750
kexue is a skill published in the GitHub repository wenhaochai/claude-plugins (17 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 637 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 2026-09-15.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.