8,211 mods tagged anthropic that install into Codex, 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.
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…
Acionamento MANUAL de failover cross-provider — LADO CLAUDE (Opus). Use quando o GPT/Codex está indisponível e o Opus está UP: o Claude ASSUME a sessão interrompida do Codex e a continua (event=gpt-down); ou quando o GPT/Codex volta, o Claude disponibiliza o estado e o Codex realinha a própria casa (event=gpt-up).…
When the user asks for an image, illustration, icon, banner, hero graphic, logo concept, mockup, or any visual asset that needs to be a real bitmap file (PNG/JPEG), use this skill. It generates real AI raster images via the user's locally-installed Codex CLI (gpt-image-2 model), accessed through Desktop Commander MCP…
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…
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 3mo 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.
Model Context Protocol server for retailerapi.com — unified product data across major US retailers (Walmart, Amazon, eBay, Target, Best Buy, Lowe's, Home Depot) plus universal URL passthrough for every Shopify store and any retailer that ships Product JSO. Runs locally from the @retailerapi/mcp npm package.
MCP server "clinical-doc-agent" as configured in Aditya-Khadye/mcp-clinical-doc-agent. Launched with uv --directory . run mcp-clinical-doc-server.
★not rated 1 3mo agoA
tokens not measured
originalMIT
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: