Two complementary modern-C++ (C++17) native-addon skills for Claude Code. resource-review traces object and resource lifetimes and reports only proven memory/resource defects (use-after-free, double-free, leaks, out-of-bounds, integer overflow, data races, Node-API handle/reference/threadsafe-function misuse), using a.
★not rated 4 5d agoA
tokens not measured
originalMIT
A team of agents for planning, researching, analyzing, writing, and reviewing social-science academic papers, with outputs in Word and Markdown formats.
★not rated 4 1mo agoA
tokens not measured
originalMIT
Copilota open-source per la partita IVA: forfettario (tasse, scadenze, idoneità) e SRL in costruzione, con confronto tra i due regimi — sempre citando le fonti. Non sostituisce il commercialista.
★not rated 4 1mo agoA
tokens not measured
originalMIT
Hard-blocks dependency additions, bumps, and downgrades until a fresh, source-cited version check is recorded. Supports npm, pip, Poetry/uv, Cargo, and NuGet.
Puts the right rules in context on every prompt, automatically — built for full-stack developers moving across frontend, backend, and SQL in one session, researchers working in bare or LaTeX-only directories, and teams who want adversarial review (security red/blue team, code critic) before merge. 222 rules across 30…
★not rated 4 9d agoA
tokens not measured
originalMIT
Your agent writes the code, a different model tries to break it, and only what survives ships. Cross-model, edit-locked review with a machine-readable verdict, gated merges, durable decisions, stuck-loop and timeout guards, and read-only reasoning one-shots. Harness-neutral.
Vigilant Claude Code quota plugin — Claude reads its own quota during long tasks and gracefully sleeps through the reset instead of hitting the wall mid-work.
★not rated 4▲
+1 4mo agoA
tokens not measured
originalMIT
Route work through the smallest sufficient loop: handle bounded tasks directly, fan out clear branches, or coordinate durable app-rooted Claude and Codex workrooms with provider-neutral status and git lifecycle tracking.
Peer AI agents coordinate through markdown messages in shared channel folders — group chat / blackboard, no orchestrator, autonomous zero-token waiting, cross-platform.
★not rated 4
changed yesterdayA
tokens not measured
originalApache-2.0
Decision-centric memory system for AI coding agents. Store conclusions, not notes. OODA-driven reasoning artifacts with priority matrix, invalidation triggers, and seed activation.
Data science plugin for LLM agents. Connects to 13 database types, 20+ file formats, graph/RDF sources, and provides 8 analytical domains with 70 MCP tools, 18 skills, and 11 agents.
★not rated 4 1mo agoA
tokens not measured
originalApache-2.0
Agent skills for live flight and hotel pricing: cheapest dates, fare watch, trip planning, hotel search, rate parity. Independent APIs, not affiliated with Google or Booking.com.
★not rated 4▲
+1 10d agoA
tokens not measured
originalMIT
Qualifies whether an AI workflow needs a graph, then designs a bounded graph of specialist loops or agents with typed node, edge, state, handoff, join, verification, budget, permission, recovery, and human-approval contracts. Produces a Mermaid view, machine-readable contract, and vendor-neutral orchestration skeleton.
★not rated 4▲
+2 12d agoA
tokens not measured
originalMIT
A comprehensive suite of Claude Code ultracode multi-agent workflow scripts, along with a workflow-authoring skill, a live-progress statusline, enhanced observation UI, and diagram tools. Everything composes into a full-lifecycle orchestration pipeline.
★not rated 4 1mo 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: