Read-only iOS App Store pre-submission check: static scan, optional fastlane precheck, guideline drift watch, Pierre explains every FAIL and WARN, and semantic deep review before you submit.
Use when writing, reviewing, or modifying any code. Applies complexity-driven design principles from A Philosophy of Software Design, 2nd Edition by John Ousterhout.
★not rated 6 3mo agoA
tokens not measured
originalMIT
Agent skills for the River API — write correct training scripts with the river-client Python package: LoRA fine-tuning, SFT, and RL/GRPO on River-hosted models.
★not rated 6▲
+2 1mo agoA
tokens not measured
originalApache-2.0
Companion plugin for codescout MCP server. Injects the project system-prompt into subagents, warns on Read/Grep/Glob misuse, auto-reindexes stale projects, and surfaces drift warnings.
★not rated 6▲
+4
changed yesterdayA
tokens not measured
Set up and use the OpenCode 'zen' model harness in any project — route agent work to cheaper models by capability (fast=kimi-k2.6, reasoning-heavy/code-generation=glm-5.2) to save Claude's token budget, with Claude orchestrating and validating. One-command setup writes /.config/vinay-agent/config.toml and tests both m.
Divergent research on demand. Takes any idea, braindump, or PRD and spins up parallel agents across a wildness spectrum — from grounded prior-art research to fully unhinged vision quests. Then synthesizes everything. Use /recall to search past sessions across all repos.
Free company lookups straight from official public APIs across 28 jurisdictions plus global LEI resolution - no Apify token and no per-result cost. Resolve and verify a company by name or national identifier.
★not rated 6 1mo agoA
tokens not measured
originalMIT
A software-development lifecycle framework for coding agents used with Claude Code, OpenCode, Cursor, and Antigravity. An SDLC is the set of stages used to plan, build, test, and maintain software.
★not rated 6 20d agoA
tokens not measured
originalMIT
Multi-LLM Task Router Suite. runagent.py routes bounded tasks to six backends: Claude CLI, GitHub Copilot, Gemini CLI, Antigravity (Agy), Codex/OpenAI-compatible, and direct local Gemma 4 12B via llama-server (2s, no proxy). 11 expert agent personas covering adversarial patterns (red-team, debate synthesis, output va.
★not rated 6
changed 6d agoA
tokens not measured
originalMIT
SEO & GEO (Generative Engine Optimization) for websites. Optimize for AI search engines (ChatGPT, Perplexity, Gemini, Copilot, Claude) and traditional search (Google, Bing). Includes Princeton GEO research methods for +40% AI visibility.
Search your team's Skills Board library over MCP and get the install command for a saved skill or a published collection.
★not rated 6 todayA
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: