12,602 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Summarize video URLs or local videos into timestamped Markdown notes from complete transcripts and actual visual evidence, with adaptive sampling and targeted visual follow-up. Supports Bilibili, YouTube, Douyin and Kuaishou.
Natural-language time tracking — the user says what they did in plain language, you parse it into Activity + Minutes + Date and write it to their Notion database; anything uncertain you mark To-confirm and BATCH-ASK rather than fabricate. Use when the user reports time spent (e.g. "read papers for two hours", "hit the…
Route token-heavy context, noisy shell logs and output through the smallest measured CLI or projection before loading heavy tools; recall past agent sessions before re-deriving; fan out to free lanes; benchmark cheap subagent workflows without broad prompt bloat.
Multi-account email MCP server for Gmail, IMAP, and JMAP: search, send, drafts, labels. Runs locally from the mailbox-mcp npm package. Needs 1 environment variable to run.
★not rated 7 8d agoA
tokens not measured
originalMIT
Schedule AI prompts to run later through this repo's PromptQueue runner. Use when the user says limits reset at a time, asks to send or paste a prompt later, or asks to queue a prompt for Claude, Codex, Cursor, Antigravity, ChatGPT, Gemini, Copilot, or another AI tool.
A set of rules that makes the AI act as a demanding workplace mentor using management ideas associated with large technology companies. It asks about goals, points out weak parts of a plan, and tracks next steps.
Switch back and forth between Claude Code, Codex, and beyond — gives Claude searchable access to every coding-agent session on this machine (local-only, read-only).
★not rated 7 1mo agoA
tokens not measured
originalMIT
Shorthand-first communication mode for token reduction w/ better readability than caveman mode. Compresses resps through consistent abbreviations, symbolic links, and dropped filler while keeping technical precision and exact literals. Use when user says "steno mode", "shorthand mode", "compressed resps", "token…
Workspace agent that executes tasks assigned by humans or supervisors, communicates progress via reply, and manages task lifecycle within a specific AgentRQ workspace.
Manage Johnny.Decimal systems with AI-assisted inbox processing, classification, JDex maintenance, system setup, task management, and next-action dashboards using jdtodo.txt. Supports single and multi-system (SYS.AC.ID) configurations.
★not rated 7 7mo agoA
tokens not measured
originalApache-2.0
Fast, token-efficient, context-aware control of macOS WeChat through verified FastBridge MCP tools with Computer Use fallback. Use when Codex must read, monitor, or reply in WeChat; understand a long-running chat; send text, emoji, stickers, or files; run an authorized customer autopilot; or resolve an imperfect chat…
Windows notification MCP server for AI development tools - Get desktop notifications when AI tasks complete. Runs locally from the mcp-windows-notify npm package.
★not rated 7 1y agoA
tokens not measured
originalMIT
Operate the agent-email CLI to create disposable inboxes, poll for new mail, retrieve full message details, and manage local mailbox profiles. Use when the user needs terminal-based email inbox access for LLM or agent automation workflows.