Keeps coding agents on your design system: catches palette colors, native elements and APIs your system lacks, at every edit and pull request, with the fix. Set it up once in your design-system package; every app in your monorepo gets it.

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

Rules and checks that make Claude Code look around a change, not just at the lines it writes: ten questions before code, a reviewer that didn't write it, proof before done, bugs fixed as a class.

Framework-aware code intelligence MCP server — 91 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity

Engineering discipline for AI coding agents: question the request, verify against current docs, plan, build test-first on the cheapest capable model, review with a second model family, prove it before saying done. One repo for Claude Code, Codex, Antigravity, Cursor, Gemini CLI and OpenCode.

Framework-aware code intelligence MCP server — 91 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity

Enables coding agents to audit projects locally for token waste, calculate model arbitrage and pricing alternatives, and make request bodies cache-friendly, with payload optimization sending the supplied request body to the TokenZero service.

Enables AI agents to request Jupiter swap quotes, build unsigned Solana swap transactions for user signing, and access paid token-risk and wallet-portfolio data via x402.

Enables AI agents to answer data-center siting questions by querying a live facility registry, per-metro market intelligence, real-time grid fuel mix and demand, and leasable capacity listings, including a one-call planner that combines these into ranked, cited answers. Results are fetched live per request, keyless, with optional API keys for fuller responses.

Search and buy products from sellers and verified warehouses, sell surplus stock, post requests.

Gives AI agents one MCP interface to inspect CI health and flaky tests, pull request flow, delivery/DORA metrics, dependency risks, community health, insights, and org portal data across GitHub repositories. It exposes 11 core tools by default and all 35 with --tools all.

Enables an AI agent to ask your phone for its current location on demand with consent, via a self-hosted relay and OAuth instead of API keys. The relay requests a fresh GPS fix and returns the answer without keeping location history.

Craft is a Claude Code plugin that asks you the product questions and works out the technical ones. Features get planned, built, and tested, with your codebase read-only until you approve the work. Point at a live page to change it. The calls you make - decisions, design tokens, the tweaks you loved - carry into every build after.

Shape rough requests into evidence-backed /goal completion contracts — an Agent Skill for Claude Code and Codex

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

Skills for issue-driven software development, from issue to change request.

DeepSeek Harness plugin: automatically adds a stable per-conversation x-opencode-session header to OpenCode / OpenCode Go provider requests — fixes 400 MissingSessionID and keeps OpenCode's session affinity / prompt-cache routing working.

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation. Use this skill whenever the user asks for a council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-te

Kimi for Claude Code and Codex: code questions, independent reviews, bounded fixes, autonomous goals, parallel tasks, and MCP tools through your local Kimi Code CLI. Available through GitHub marketplaces and npm.

Automatic strong/cheap model-tier routing for DeepSeek Harness: intent-gated tier landing on the agent/request waterfall, plan-mode handoff (strong plans, cheap implements), deterministic high-risk guards on tools/pre-execute, failure escalation with TTL

Quality gate for AI/Codex-generated pull requests: blocks TODO leftovers, leaked secrets, sloppy commits and red CI before they reach main.

Enables AI agents to drive policy evaluation over MCP by starting executions, answering policy questions from case evidence, and reading deterministic outcomes with reasoning traces, while the runtime controls which questions are asked and how answers combine.

Enables Claude Code users to inventory the MCP servers, skills, commands, agents and plugins installed on their machine, estimate how many tokens each one adds to every request, and switch them off per project or globally, including across other AI coding tools. It also monitors live sessions to report real token usage and the savings achieved from disabled items.