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/autoresearch)<a href="https://agentmods.dev/plugins/emaballarin/ccplugins/autoresearch"><img src="https://agentmods.dev/badge/plugins/emaballarin/ccplugins/autoresearch/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/autoresearch"><img src="https://agentmods.dev/badge/plugins/emaballarin/ccplugins/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ar 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 6d 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": "ar",
"version": "0.4.10",
"description": "ar — autoresearch: a skill-only autonomous experiment loop. Propose → measure → keep winners → repeat, against any numeric objective, with noise-floor gating so nothing is banked on noise. Five skills: /ar:start opens a run (dedicated branch + baseline noise floor), /ar:resume advances it, /ar:status prints read-only state, /ar:report writes the final summary, /ar:stop ends the loop. State lives in the target repo's ./.ar/ only. No hooks, no MCP, no settings patching.",
"author": {
"name": "Emanuele Ballarin",
"email": "[email protected]"
},
"homepage": "https://github.com/emaballarin/ccplugins/tree/main/plugins/autoresearch",
"repository": "https://github.com/emaballarin/ccplugins",
"license": "MIT",
"keywords": ["autoresearch", "experiment", "optimisation", "benchmark", "ablation", "research-loop", "statistics"]
}
What it installs
The manifest is a name and a version. 5 skills travel with it, and installing the plugin installs all of them — 603 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 6d ago Changed c1c4dc2b9203
- 12d ago Changed e28e61b76dd1
- 13d ago Changed b996e2ce1784
- 19d ago Changed bc31eddaabc3
- 22d ago Changed bbeaccec1275
- 1mo ago Changed e89171dbb82f
- 1mo ago First seen · 14 lines scan A c426bf33fa57
ar is a plugin published in the GitHub repository emaballarin/ccplugins (4 stars, last pushed 7d 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.