16,154 mods tagged anthropic that install into Claude Code, measured the same four ways as everything else here: what each costs in tokens on every session, what a security scan found and why, whether it is the original, and what changed.
Distill technical discussions into compact, tagged decision entries with a live registry of open questions, all version-controlled in your repo and queryable by Claude.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Use this agent when you need to actively test applications, APIs, infrastructure, or code for exploitable vulnerabilities. This agent thinks like an attacker and finds entry points before real attackers do. It complements the security-master agent through practical attack simulation. This agent should be used…
Give any local port (Gradio, Streamlit, FastAPI, webhook receiver, dev server, Docker container) a permanent HTTPS URL on a domain the user owns - in one command, no deployment. Use when the user says "my Gradio share link keeps changing", "replace share=True with a permanent URL", "stable URL for localhost:7860"…
Encrypted peer-to-peer text messaging between agent sessions (Claude Code or other CLI agent harnesses on the same machine) running in separate terminals. Use this whenever the user wants to talk to another agent, message another Claude, coordinate with another agent, open/create/join/enter a room, send text to a…
Manage Yandex Tracker spaces through the REST API. Use when Codex needs to work with any documented Tracker API function: issues, issue filters, checklists, comments, attachments, bulk operations, fields, projects, portfolios, goals, queues, automation, boards, dashboards, components, issue types, statuses…
Complexity-based routing of tasks across four model tiers — frontier (T3), strong workhorse (T2), fast executor (T1), cheapest recon (T0). Use when planning any multi-step work, when deciding which subagent should execute a task, when writing a dispatch brief, or when an executor fails and escalation is needed.
Use to audit and clean text so it reads human-written, not machine-generated. Covers what to look for (guided by Wikipedia's "Signs of AI writing"), how to scan for the markers, how to fix them without flattening a good voice, and how to verify. Works on any prose in any project (course text, docs, articles, READMEs).…
The doaipm method (DO AI PM) — how to build products as a product manager in the AI era. Use this whenever someone plans, scopes, or builds a product, feature, prototype, app, or website; when a person describes an idea and asks how to approach it; when choosing between a low-fidelity sketch and a real prototype; or…
A startup-validation coach built from the Testing Business Ideas method (Bland & Osterwalder). Turns an idea into testable hypotheses, recommends experiments from a 44-experiment library, writes Test Cards, and drives persevere / pivot / kill decisions.
MCP server for WeFact — let Claude (Desktop, Code, Cursor) read and modify your WeFact administration via the v2 API. Runs locally from the wefact-mcp Python package.
★not rated 1 1mo agoA
tokens not measured
AGPL-3.0
MeshMind — a single MCP server that merges local codebase mapping, recency research, and token compression for AI agents. Runs locally from the meshmind npm package.
★not rated 1 2mo agoA
tokens not measured
originalMIT
MCP server "student-progress-tracker" as configured in woodstocksoftware/student-progress-tracker. Runs locally from the student-progress-tracker Python package.
★not rated 1 6mo agoA
tokens not measured
originalMIT
MCP server "LibreOfficeResumeEditor" as configured in adi2355/MCP-Resume-Editor. Runs /Users/YOUR_USERNAME/ResumeTailorGuddu/resume_editor_server.py with /Users/YOUR_USERNAME/ResumeTailorGuddu/.venv/bin/python.
★not rated 1 5mo agoA
tokens not measured
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: