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/emaballarin/ccpluginsWrote 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/emaballarin/ccplugins/ccscience)<a href="https://agentmods.dev/plugins/emaballarin/ccplugins/ccscience"><img src="https://agentmods.dev/badge/plugins/emaballarin/ccplugins/ccscience/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/emaballarin/ccplugins/ccscience"><img src="https://agentmods.dev/badge/plugins/emaballarin/ccplugins/ccscience.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ccsci 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 8d 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
{
"name": "ccsci",
"version": "0.10.1",
"description": "ccsci — research & scientific-computing skills adapted from Claude Science for stock Claude Code. Skills: literature-review (DOI-grounded, all-STEM, BibTeX export), bib-audit (verify, correct, upgrade, dedupe, rekey and tidy an existing .bib), pdf-explore (parse-once big-PDF navigation, table extraction, native-resolution figures), figure-style / figure-composer / paper-narrative (publication multi-panel figures), paper-review (human-driven peer review with Claude as second reader: line-anchored claim ledger, rubric-boundary calibration, error checks on the reviewer's drafts). Plus computational-scientist and deep-researcher subagents.",
"author": {
"name": "Emanuele Ballarin",
"email": "[email protected]"
},
"homepage": "https://github.com/emaballarin/ccplugins/tree/main/plugins/ccscience",
"repository": "https://github.com/emaballarin/ccplugins",
"license": "Apache-2.0",
"keywords": [
"science",
"research",
"literature-review",
"bibtex",
"bibliography",
"pdf",
"figures",
"scientific-computing",
"matplotlib",
"peer-review"
]
}
What it installs
The manifest is a name and a version. 7 skills, 2 agents travel with it, and installing the plugin installs all of them — 1,413 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill literature-review A 121 tokens
- Skill pdf-explore A 263 tokens
- Skill bib-audit A 190 tokens
- Skill figure-composer A 159 tokens
- Skill paper-narrative A 150 tokens
- Skill paper-review A 92 tokens
- Skill figure-style A 219 tokens
- Agent computational-scientist A 145 tokens
- Agent deep-researcher A 74 tokens
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.
- 8d ago Changed eb9756582772
- 15d ago Changed 95664f9ed4fb
- 16d ago Changed · +1 lines 7ad07693dc22
- 22d ago Changed c1a01a2e9cd0
- 25d ago Changed · +1 lines 461a014fb105
- 1mo ago Changed f692817591c9
- 1mo ago First seen · 23 lines scan A e0712ebdfec3
ccsci is a plugin published in the GitHub repository emaballarin/ccplugins (4 stars, last pushed 10d ago), licensed MIT. 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
shiny
Collection of skills for Shiny app development.
quarto
Collection of skills for Quarto document creation.
combinatorial-optimization
76 skills covering MILP modeling with Gurobi, decomposition methods (column generation, Benders, Lagrangian), all major metaheuristics (GA, PSO, SA, tabu, ALNS, BRKGA, ...), encodings and operators, classic problems (TSP, VRP, scheduling, knapsack, facility location), and optimization research workflows with numpy…
tidymodels-developers
Development tools and guides for tidymodels ecosystem packages including yardstick metrics, recipes steps, dials parameters, and parsnip models.
bibtools
A bibliography toolkit for LaTeX.
mathviz
Create, review, and render production-quality mathematical animations using Manim Community Edition.