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 getpapi/papinpx agentmods add plugins/getpapi/papi/marketplacegit clone --depth 1 https://github.com/getpapi/papiGrade A, and why
papi 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": "papi",
"owner": {
"name": "PAPI",
"email": "[email protected]",
"url": "https://getpapi.ai"
},
"metadata": {
"description": "PAPI — persistent project management for AI coding agents."
},
"plugins": [
{
"name": "papi",
"source": "./",
"description": "Persistent project management inside your AI coding tool. PAPI plans what to build next, tracks every decision, and keeps projects coherent across sessions — so a new session starts where the last one left off instead of from nothing. Connects to the hosted PAPI server over OAuth; nothing runs locally.",
"author": { "name": "PAPI", "url": "https://getpapi.ai" },
"homepage": "https://getpapi.ai",
"repository": "https://github.com/getpapi/papi",
"license": "MIT",
"category": "productivity",
"tags": [
"papi",
"project-management",
"planning",
"task-management",
"context",
"mcp"
],
"keywords": [
"papi",
"project-management",
"planning",
"task-management",
"context",
"mcp",
"productivity",
"developer-tools"
]
}
]
}
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 · 42 lines scan A d23839f3fb24
papi is a plugin published in the GitHub repository getpapi/papi (7 stars, last pushed 11d 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
astravue
Astravue plugin marketplace for Claude Code.
astravue
Connect to Astravue project management. Manage spaces, projects, tasks, subtasks, checklists, comments, time tracking, and team collaboration through natural language.
ijfw
Plugin marketplace listing 1 plugin: ijfw.
pad
Talk to your project. Pad is local-first project management for developers and AI agents — this plugin gives Claude Code a conversational Pad skill, typed shortcuts (/pad:status, /pad:capture, /pad:onboard, /pad:connect, /pad:disconnect), and consent-gated live item-change notifications.
memex
Zettelkasten-based agent memory system with bidirectional links.
talkthrough
Plugin marketplace listing 1 plugin: talkthrough.