Eco mode for Claude Code: minimize token consumption with critical findings intact. Ships /eco and /eco-max (frugality rules, with a low reasoning-effort override), an Eco output style, /eco audit and /eco report, opt-in enforcement hooks, and a benchmark harness. Measured -35% to -57% output tokens on the same task…
★not rated 33 24d agoA
tokens not measured
originalMIT
Mountain route research for North American peaks: automated route beta reports with weather forecasts, avalanche conditions, daylight windows, and trip reports aggregated from 10+ sources including PeakBagger, SummitPost, WTA, and AllTrails.
★not rated 33 1mo agoA
tokens not measured
originalMIT
ES: Vuelve a Claude en tu contra para criticar a fondo una idea, un plan o un proyecto entero — sin validar ni suavizar — por ocho ángulos, con investigación de fracasos reales y un veredicto priorizado de qué arreglar. EN: Turn Claude against you to harshly critique an idea, plan, or whole project across eight angles.
★not rated 33 3mo agoA
tokens not measured
originalMIT
Live music engine for Claude Code. Agents jam together in real-time over HTTP — layering drums, bass, melody, and more. Conductor mode, context-aware DJ, mix snapshots, 22 presets, 8 vibes. No browser or API key needed.
★not rated 33 3mo agoA
tokens not measured
AGPL-3.0
P2P agent capability network — discover and request capabilities from peer agents when you lack TTS, image gen, video, OCR, specialized data, or any API-dependent skill. Pay with credits.
★not rated 33▲
+1 2mo agoA
tokens not measured
originalMIT
Kage manages your memory and agents. It briefs and runs agents in isolated git worktrees for a single run or a multi-wave goal, re-runs the checks itself instead of trusting the agent's report, and remembers what it learns so each brief is smarter than the last.
★not rated 33▲
+1 12d agoA
tokens not measured
GPL-3.0
Multi-agent cryptocurrency intelligence system with 7 specialized AI agents, 9 MCP servers (95 tools), cognitive learning, and self-evolving capabilities for comprehensive market analysis and paper trading.
★not rated 33 17d agoA
tokens not measured
originalMIT
Live Asian-priced football & basketball odds + scores over the InferSports REST API: who's favored, the live score, today's matches and a specific day's schedule (timezone-aware), what's worth watching, a one-line pre-match brief, one normalized sharp line, the sharp de-vigged fair probability, whether a…
★not rated 33 3mo agoA
tokens not measured
originalMIT
8 Claude Code and Codex skills for Threads (Meta) marketing: single-post and multi-post thread writing, AI-tell humanizer with pre-publish audit, viral hook extraction, reply and quote drafting, profile optimization, content repurposing, audience insights, and weekly content planning. Publora is the default publish…
★not rated 33▲
+13
changed todayA
tokens not measured
originalMIT
GraQle dev intelligence layer: graph-powered codebase reasoning, impact analysis, and governed edits via MCP, plus governed-workflow skills and an optional governance gate hook.
Quizzes you on the code Claude Code just wrote — and blocks the session until you pass. Recover the understanding you lose when you orchestrate instead of author.
Two Claude Code engineering skills bundled as one plugin: review-loop (cross-LLM iterative code review with Codex or Gemini as peer) and harness (cybernetics-based Planner→Generator→Evaluator→Retro orchestration for complex tasks).
★not rated 32 3d agoA
tokens not measured
originalApache-2.0
Design skill for Claude Code. Research, diverge, decide, draft, refine — iterative loops with fresh evaluator agents that treat every design as unfinished until proven otherwise.
★not rated 32 5mo agoA
tokens not measured
originalMIT