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.
/plugin marketplace add sattyamjjain/proofloopnpx agentmods add plugins/sattyamjjain/proofloop/marketplacegit clone --depth 1 https://github.com/sattyamjjain/proofloopGrade A, and why
proofloop 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 yesterday.
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": "proofloop",
"owner": {
"name": "Sattyam Jain",
"email": "[email protected]"
},
"metadata": {
"description": "Universal quality judge for Claude Code and Cowork skill/agent executions"
},
"plugins": [
{
"name": "proofloop",
"source": "./",
"description": "Auto-evaluates skill and agent execution quality with 7-dimension scoring, configurable rubrics, and dual-mode operation.",
"version": "3.1.1",
"category": "quality-assurance",
"tags": ["judge", "evaluation", "quality", "scoring", "LLM-as-judge"],
"license": "MIT",
"homepage": "https://github.com/sattyamjjain/proofloop",
"repository": "https://github.com/sattyamjjain/proofloop"
}
]
}
What ships with it
1 file beside marketplace.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.
- yesterday First seen · 24 lines scan A c91e005e6f79
proofloop is a plugin published in the GitHub repository sattyamjjain/proofloop (5 stars, last pushed 2mo 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
katalepsis
Verify understanding after AI work through intent-scented entry points — /grasp (κατάληψις: a grasping firmly).
oh-my-claude
Plugin marketplace listing 1 plugin: oh-my-claude.
harness-eval
Evaluate AI agent setups for best practices, redundancy, security, and cross-component issues.
forge-harness
Plugin marketplace listing 2 plugins: fh-meta, fh-commons.
brana
AI development system — skills, agents, and hooks for systematic software engineering with Claude Code.
bankstatemently
Official Bankstatemently plugins — convert bank statements directly from Claude.