Adversarial co-generation engine — generates code and adversarial attacks from the same spec, concurrently. Adds /gauntlex:run and friends, plus the gauntlex MCP server.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Rewrites Claude-English into plain English: sycophantic openers, hedging filler and padded phrasing out, facts, code blocks, names and numbers untouched. Runs an open-weights model on dedicated GPUs, so text never reaches a commercial AI provider.
★not rated 1 todayA
tokens not measured
originalMIT
Your personal context, served to Claude Code over MCP. Map each folder to one of your @handle profiles so every session in that folder reads the right context.
★not rated 1 21d agoA
tokens not measured
originalMIT
Dependency graph, blast-radius analysis, and gate-style checks for local TypeScript and JavaScript repositories. Predict what breaks before you commit.
★not rated 1 todayA
tokens not measured
originalMIT
Corporate ownership intelligence for GTM teams — parent companies, PE backing, corporate families, and portfolio siblings, over lists of up to 5,000 companies.
★not rated 1 14d agoA
tokens not measured
originalMIT
Give your AI agent memory across sessions. Search and recall past conversations from Claude Code and Cursor history — no context lost, no re-explaining.
★not rated 1 6mo agoA
tokens not measured
originalMIT
Modern Python 3.12+ patterns your AI agent should use. Type hints, async/await, Pydantic v2, uv package manager, match statements, and project structure.
★not rated 1 6mo agoA
tokens not measured
originalMIT
Compress documentation, prompts, and context into minimal tokens for AGENTS.md. Based on Vercel's research showing compressed passive context achieves 100% pass rate vs 53% baseline.
★not rated 1 6mo agoA
tokens not measured
originalMIT
Always-on security guardrails for AI-generated code. Catches hardcoded secrets, missing auth, insecure database rules, and the 20 things AI agents forget before you deploy.
★not rated 1 6mo agoA
tokens not measured
originalMIT
Scaffold a mobile-spine workspace — a meta-repo coordinating four Claude Code subagents (api / pm / android / ios) for mobile teams whose Android, iOS, and Backend live in separate repos.
★not rated 1 2mo agoA
tokens not measured
originalMIT
45 production-grade compliance skills for AI coding agents. Cosmetics, food, electronics, toys, textiles, supplements, medical devices, and more. Substance checks, labeling, market entry, customs, certifications. MIT licensed. Powered by the Cleo Legal API.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Audit live web pages for fake/mock data — 5-phase Playwright + Claude Code skill that classifies every visible value as REAL, MOCK, LLM, HARDCODED, BROKEN, or UNKNOWN.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Run a task as an evolved multi-agent ORG. The compose-org skill makes the running Claude embody a proven team — one subagent per specialist talent — then grades and records the result so good teams get reused on similar future tasks. Backed by the liquid-org CLI (plan / compose / record).