Skill Claude CodeCodex
This skill should be used when the user asks about "test validation", "assertion strategies", "regex vs contains", "handling flaky tests", "validation failures", "expected vs actual", or needs guidance on choosing validation approaches and handling edge cases.
Command
Interactively add a new test definition to the test suite.
Command
Generate test execution report in various formats.
Plugin Claude Code
Verify and enforce use of latest stable library and package versions using live documentation lookups. Prevents outdated version recommendations, security vulnerabilities from stale dependencies, and deprecated API usage across 13+ package ecosystems.
Command
Verify and enforce use of the latest stable library/package versions using live documentation lookups instead of training-data knowledge. Use PROACTIVELY whenever: (1) Recommending or selecting a library, framework, or package version, (2) Adding dependencies to any project (package.json, pyproject.toml…
Skill Claude CodeCodex
Verify and enforce use of the latest stable library/package versions using live documentation lookups instead of training-data knowledge. Use PROACTIVELY whenever: (1) Recommending or selecting a library, framework, or package version, (2) Adding dependencies to any project (package.json, pyproject.toml…
Plugin Claude Code
Recursive Language Model integration for Claude Code using rlm-rs CLI. Enables processing documents far exceeding context windows via chunking and recursive sub-LLM calls.
Agent
Efficient chunk-level analysis agent for RLM workflow. Use this agent when processing individual chunks from large documents that have been split by rlm-rs. Returns structured JSON findings.
Agent
Result aggregation agent for RLM workflow. Use this agent to synthesize findings from multiple rlm-subcall chunk analyses into a coherent, comprehensive answer.
Command
Initialize the RLM database for storing buffers and state.
Command
Load a file into an RLM buffer with chunking.
Command
Run a query against loaded RLM content using the full RLM workflow.
Command
Show current RLM state including buffers and database info.
Skill Claude CodeCodex
This skill should be used when the user asks about "chunking strategies", "how to chunk a file", "semantic vs fixed chunking", "chunk size selection", "overlap settings", or needs guidance on selecting the appropriate chunking approach for RLM processing.
Skill Claude CodeCodex
This skill should be used when the user asks to "process a large file", "analyze document exceeding context", "use RLM", "recursive language model workflow", "chunk and analyze a file", "handle long context", or needs to work with documents too large to fit in the context window. Orchestrates the full RLM loop using…
Plugin Claude Code
Craft-focused design system management powered by Subcog memory. Build interfaces with elegance, consistency, and semantic memory.
Command Claude Code
Capture design patterns, tokens, or decisions to Subcog memory.
Command Claude Code
Extract design patterns from existing codebase and capture to Subcog memory.
Command Claude Code
Initialize aesth skill with Subcog context. Loads design system for current project.
Command Claude Code
Show current design system state from Subcog including direction, tokens, patterns, and decisions.
Command Claude Code
Validate code files against design tokens, craft principles, and design direction stored in Subcog.
Skill Claude CodeCodex
Interface design with craft and consistency. For dashboards, apps, tools — not marketing sites. Uses Subcog for persistent design memory.
Instructions file GitHub Copilot
Copilot instructions for zircote-plugins/aesth, covering copilot instructions, project overview, key components, plugin structure and development guidelines.
Instructions file
Claude Code instructions for zircote-plugins/aesth, covering claude.md, architecture, key concepts, memory-first design and memory types.