Create and manage ad campaigns on Meta, Google, TikTok, and more. Spy on competitor ads across ad libraries. Use when you need to launch a campaign, find out why ROAS dropped, see what ads a competitor is running, or pull a performance report. Manages campaigns, ad sets, ads, and keywords. Uploads media. Pulls…
★not rated 13 9d agoA
tokens not measured
originalMIT
Wiki-first research that compounds. Binds each run to a wiki knowledge base; future runs read what prior runs filed before hitting the web. v0.1.0 inverted pipeline (plan → curate → fetch → ingest → distill → compose → verify → finalize) with zero-network, citation-consistent claim verification — opt-in live-source…
★not rated 13
changed 2d agoA
tokens not measured
originalApache-2.0
Whether, then how, then shipped. /ideation:brainstorm pressure-tests ideas in conversation; the evidence-gated interview, stress-tested by adversarial plan critics, turns a yes into an interactive HTML contract and Markdown specs; /ideation:autopilot runs all phases on a deterministic workflow engine. Watched runs…
★not rated 13 12d agoA
tokens not measured
originalMIT
A multi-agent system for writing Chinese web fiction, using a rolling chapter workflow and editing intended to make the output sound less machine-generated.
★not rated 13 4mo agoA
tokens not measured
originalMIT
SvelteKit and Svelte 5 done right. Runes ($state, $derived, $effect), load functions, form actions, SSR patterns, and modern Svelte your AI agent should follow.
★not rated 13 6mo agoA
tokens not measured
originalMIT
Fable 5's working loop for hard tasks: decompose by verification boundaries, verify against the world, choose next by plan-change. Includes scout + refuter agents and a preflight script.
AI-driven intercepting proxy + rootless execution sandbox for web pentesting. Installs the burpwn skill, which teaches the agent to create a session and route target-facing network commands through burpwn exec so their traffic is captured, MITM-decrypted, searchable, replayable, and live-interceptable. Requires the.
★not rated 13 22d agoA
tokens not measured
AGPL-3.0
Sits between Claude Code and your codebase and hands back a short file:line list instead of dumping source into the chat. It uses a real language server when it can (clangd / Roslyn / tsserver / pyright), tree-sitter when there's no toolchain, and a fuzzy search built from your repo's own naming when you don't know…
Load the architecture decisions governing a change, check plans against them, audit existing code and documentation for missing decisions, and draft new records deliberately — driven by the adr CLI.
★not rated 13▲
+1
changed todayA
tokens not measured
originalApache-2.0
Use Titen's evidence-grounded collaborative memory. The local stdio mode needs no configuration; a served Titen endpoint is the alternative for a shared store.
★not rated 13▲
+1 5d agoA
tokens not measured
originalApache-2.0
Connect Claude Cowork to Claude Code on your own computer (macOS or Linux). Cowork hands a task to a local Claude Code agent (and can run approved scripts too); the bridge is idempotent, streams progress, and is token-protected. Install with one command; it sets up a global Cowork skill so every session connects…
★not rated 13 9d agoA
tokens not measured
originalMIT
Turn any Claude Code session into a long-horizon master orchestrator: pick the right dynamic-workflow paradigm and keep the main thread productively advancing across compaction and sessions.
Local-first cognitive substrate for neurodivergent professionals. Bundles the five NeuroDock MCP servers and a set of ND-aware skills for communication decoding, task decomposition, working-memory recall, and clinical guardrails.
★not rated 13▲
+2 yesterdayA
tokens not measured
AGPL-3.0
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: