Deep Ass Research (DAR) — deep, multi-source, primary-sourced research into a backlinked Obsidian vault: fan-out scout/diver subagents, adversarial verification, and a synthesized Map-of-Content + report.
★not rated 4 1mo agoA
tokens not measured
originalMIT
Adaptive socratic mentor for Claude Code. One dial: the level decides how much of the work is yours. At 3 it writes skeletons and every function body is yours; at 5 it writes nothing and just asks. A PreToolUse gate enforces it, so levelling up means it does less for you, not more.
★not rated 4
changed 9d agoA
tokens not measured
originalMIT
Ask Claude for your plan usage and switch accounts in-conversation: getusage returns session, weekly, and per-model limits from the official Anthropic usage endpoint; listaccounts / saveaccount / switchaccount manage named Claude Code logins (PRO, PERSO) without a browser.
★not rated 4
changed todayA
tokens not measured
originalMIT
Puts the project's committed mnema record into the session's opening context without the agent asking, and connects the mnema MCP server so it can record its own work.
★not rated 4
changed 2d agoA
tokens not measured
originalMIT
Your team's coordination bus: shared channels and DMs between teammates' AI coding agents, task claims with leases and dependencies, presence, shared notes, resource locks and real-time wakeups. Requires BUSURL and BUSTOKEN in the environment.
★not rated 4 1mo agoA
tokens not measured
originalMIT
Intelligent permission gate for Claude Code shell, file, search, Skill, and MCP tool surfaces. AST-parses Bash commands, guards file reads/writes, and blocks configured tool invocations. Defers benign asks to CC's resolver so the prompt UI shows the 'Yes, and don't ask again for X' button, while keeping a deny floor…
Make AI-generated content undetectable. Rules that prevent em dashes, buzzwords, over-formatting, narrating comments, git co-author trailers, and uniform sentence structure.
★not rated 4 6mo agoA
tokens not measured
originalMIT
Cross-agent prompt pocket: remember your most-used prompts and pick one to run; auto-scans Claude Code, Codex and OpenCode sessions to record prompts repeated 7+ times. Forged by agent-plugin-kit.
★not rated 4 2mo agoA
tokens not measured
originalMIT
★not rated 4 5mo 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: