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.
npx agentmods add plugins/potpie-ai/potpie/claude_plugin/plugin marketplace add potpie-ai/potpiegit clone --depth 1 https://github.com/potpie-ai/potpieGrade A, and why
claude_plugin 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": "potpie",
"description": "Project-memory context engine for Claude Code: surfaces preferences, prior bugs/fixes, infra topology, timeline context, and durable-capture prompts. Hooks are model-free; the in-session harness decides what is true and writes semantic graph mutations.",
"version": "0.1.0",
"author": {
"name": "Potpie"
},
"keywords": [
"context",
"memory",
"knowledge-graph",
"potpie",
"hooks"
],
"hooks": "./hooks/hooks.json"
}
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.
- yesterday First seen · 17 lines scan A 67a79dc4d7a3
claude_plugin is a plugin published in the GitHub repository potpie-ai/potpie (5,702 stars, last pushed 2d ago), licensed Apache-2.0. 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 2026-08-30.
Other plugins, from other repositories
huggingface-skills
Plugin marketplace listing 9 plugins: hugging-face-model-trainer, hugging-face-paper-publisher, hugging-face-datasets, hugging-face-evaluation, hugging-face-tool-builder.
hugging-face-trackio
Query Trackio projects, runs, and metrics using the trackio CLI. Use when the user needs to list projects/runs/metrics, get summaries, or retrieve metric values from local Trackio databases. Supports both human-readable and JSON output formats. Covers project discovery, run inspection, metric querying, and system met.
hugging-face-skills
Agent Skills for AI/ML tasks including dataset creation, model training, evaluation, and research paper publishing on Hugging Face Hub.
mechanist
Plugin marketplace listing 1 plugin: mechanist.
webfetch
Self-hosted web search for LLM agents - same accuracy as hosted websearch at a third of the cost.
lethe
Persistent memory across Claude Code sessions. Markdown-first storage, hybrid BM25 + dense retrieval, clustered retrieval-induced forgetting, optional Haiku enrichment.