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/IBazylchuk/paparats-mcpWrote 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/ibazylchuk/paparats-mcp/claude-plugin)<a href="https://agentmods.dev/plugins/ibazylchuk/paparats-mcp/claude-plugin"><img src="https://agentmods.dev/badge/plugins/ibazylchuk/paparats-mcp/claude-plugin/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/ibazylchuk/paparats-mcp/claude-plugin"><img src="https://agentmods.dev/badge/plugins/ibazylchuk/paparats-mcp/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
paparats 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 today.
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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "paparats",
"displayName": "Paparats",
"description": "Self-hosted semantic code search across all your repos. Search by meaning, follow callers through a symbol graph, and get exact chunks instead of whole files. Runs on your machine; your code never leaves it.",
"version": "2.13.0",
"author": {
"name": "Ilya Bazylchuk",
"url": "https://github.com/IBazylchuk"
},
"homepage": "https://github.com/IBazylchuk/paparats-mcp",
"repository": "https://github.com/IBazylchuk/paparats-mcp",
"documentationUrl": "https://github.com/IBazylchuk/paparats-mcp#readme",
"supportUrl": "https://github.com/IBazylchuk/paparats-mcp/issues",
"privacyPolicyUrl": "https://github.com/IBazylchuk/paparats-mcp/blob/main/PRIVACY.md",
"license": "MIT",
"icon": "icon.png",
"keywords": ["semantic-search", "code-search", "local-first", "qdrant", "multi-repo"],
"userConfig": {
"server_url": {
"type": "string",
"title": "Paparats server URL",
"description": "MCP endpoint of your Paparats server. Keep the default for a local install; use /support/mcp for the support endpoint, or the address of a shared server.",
"default": "http://localhost:9876/mcp",
"required": false
}
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 60 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.
- today First seen · 29 lines scan A 6bcb3a00ee42
paparats is a plugin published in the GitHub repository IBazylchuk/paparats-mcp (11 stars, last pushed today), 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 2026-10-26.
Other plugins, from other repositories
sverklo-skill
Teaches Claude how to use sverklo's code intelligence MCP tools — semantic search, blast-radius, PR review, codebase audit, persistent memory.
memtrace-skills
Memtrace skills for codebase exploration, code search, relationship analysis, temporal evolution, blast radius impact, code quality, graph algorithms, API topology, GitHub PR code review, multi-agent fleet coordination (branch-scoped intents, conflict classification, and agent-judged Class C resolution), and…
full-audit
Exhaustive audit of an entire area (codebase/docs/skills/memory/config): deterministic sweep, content review and rule dry-run (three layers), anti-false-positive kill-test, persistent coverage map.
omen-development
Code analysis skills for active development: find bugs, assess impact, plan refactoring, audit architecture, and more.
codeseeker
CodeSeeker - Intelligent code understanding with semantic search, knowledge graphs, and auto-detected coding standards.
superbased
Token, cost and cache observability for Claude Code. Wires the SuperBased Observer MCP server plus its session/tool lifecycle hooks. Requires the observer binary already on your PATH (npm i -g @superbased/observer, or pipx install superbased-observer) — this plugin is wiring only and installs no binary.