verify

Provenance-bound durable memory with immutable records, append-only review state, active-only recall, and offline semantic recall via a first-party rag provider.

1 skill · 4 commands · 1 MCP server · hooks

Portable, bounded, verified task-state handoffs with manual write/resume commands, a read-only compiler, and deterministic validation.

1 skill · 2 commands · 1 agent

Measure agent token usage from local host records, and settle tool savings claims with controlled A/B runs that require a preserved answer.

2 skills · 2 commands

Exhaustive review of a corpus too large to read at once: hashed unit inventory, bounded resumable shards, and a coverage ledger that separates a real gap from an undecidable one.

1 skill · 1 command · 1 agent

Multi-lens evaluative review: independent adversarial, architect, consumer, and operator charters return typed findings that merge on agreement and preserve disagreement as an explicit tradeoff.

1 skill · 1 command · 1 agent

Plan-big / execute-small orchestration: a strong model plans and delegates token-heavy work to cheaper subagents.

1 skill · 1 command · 1 agent

IoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardware

5 skills · 1 command · 4 agents

Connect Claude Code directly to your CockroachDB clusters for hands-on database work — explore schemas, write optimized SQL, debug queries, and manage distributed database clusters. This plugin provides 14 tools across two active MCP backends (self-hosted MCP Toolbox and managed CockroachDB Cloud MCP Server), three specialized agents (DBA, Developer, Operator), 32 skills across 6 operational domains, and built-in safety hooks.

34 skills · 3 agents · 3 MCP servers · hooks

Portable operating method: session lifecycle agents, pre-ship code review, deploy with live verification and state doc update, and production log health check

5 agents

CockroachDB plugin for Claude Code — explore schemas, write optimized SQL, debug queries, and manage distributed database clusters directly from your AI coding agent.

34 skills · 3 agents · 3 MCP servers · hooks

A second brain for Claude Code + Obsidian inspired by Karpathy's LLM Wiki gist. Turn any LLM CLI into a disciplined wiki maintainer: incrementally ingest sources into a persistent, interlinked markdown vault; update entity/concept/source pages; flag contradictions; maintain index and append-only log. Knowledge compounds instead of being re-derived by RAG on every query. Ships 3 sub-agents (wiki-ingestor, wiki-librarian, wiki-linter), 5 slash commands (/wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log), 8 Python tools (stdlib only: init_vault, ingest_source, update_index, append_log, wiki_search BM25, lint_wiki, graph_analyzer, export_marp), 8 reference docs, full vault templates (CLAUDE.md, AGENTS.md, cursorrules, 5 page templates), and a worked example vault. Cross-tool compatible with Claude Code, Codex CLI, Cursor, Antigravity, OpenCode, and Gemini CLI.

1 skill · 5 commands · 3 agents

Skills for image generation and editing with GPT Image 2 (and OpenAI-compatible image endpoints), with three runtime modes and 70+ structured prompt templates.

1 skill