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/unshDee/proofragWrote 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/unshdee/proofrag/proofrag)<a href="https://agentmods.dev/plugins/unshdee/proofrag/proofrag"><img src="https://agentmods.dev/badge/plugins/unshdee/proofrag/proofrag/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/unshdee/proofrag/proofrag"><img src="https://agentmods.dev/badge/plugins/unshdee/proofrag/proofrag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
proofrag 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 12d 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": "proofrag",
"version": "0.9.0",
"description": "Evaluate a RAG/LLM app: generate a golden set from your docs, run LLM-as-judge + retrieval metrics, and produce a shareable HTML scorecard with a CI gate.",
"author": { "name": "Ansh Dawda", "email": "[email protected]" },
"homepage": "https://github.com/unshDee/proofrag",
"repository": "https://github.com/unshDee/proofrag",
"license": "MIT",
"keywords": ["rag", "llm", "evaluation", "llm-as-judge", "retrieval", "skill"]
}
What it installs
The manifest is a name and a version. 1 skill, 1 command travel with it, and installing the plugin installs all of them — 117 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 12d ago Changed 4f7f66e9c301
- 1mo ago First seen · 11 lines scan A b39148bf668c
proofrag is a plugin published in the GitHub repository unshDee/proofrag (2 stars, last pushed 12d 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
veritasreason
Full-stack knowledge graph skills: semantic extraction, decision intelligence, context graphs, reasoning, explainability, ontology, provenance, deduplication, visualization, and multi-format export.
clip-aware-embeddings
Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Activate on "CLIP", "embeddings", "image similarity", "semantic…
mixedbread-skills
Agent skills for search, RAG, parsing, completions, and model harnesses with Mixedbread.
kalera-munin
Kalera Munin - Long-Term Memory with GraphRAG Context Cores for Gemini CLI.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.