Search

Ask your AI questions about its own code changes — from a Git diff viewer.

Claude Code skill for writing system prompts — 14 sections, 12 common mistakes, 4 prompt types

Instinct Engine that scans recent sessions for recurring patterns and turns them into concrete captures.

First-principles analyst. Surfaces hidden assumptions, finds foundational truths, identifies the high-leverage move.

Self-improving measurement layer for Claude Code. Reads JSONL session data, computes effectiveness metrics, writes behavioral rules into CLAUDE.md. Companion to claude-daily-journal and claude-insights.

Conversational daily journaling for Claude Code. 34-floor emotional altitude scale, optional advisory panel, Obsidian markdown.

Temporal Agency for Claude Code: turns to-dos into time-boxed calendar blocks, protects biological anchors first, tracks scheduled vs shipped

Python client for ThinTokens — convert JSON to TOON and save LLM tokens

Agent-Native CLI design & review skill — design CLIs that serve humans, AI agents, and orchestration systems simultaneously

Extract your honne — the real working self underneath tatemae — from your Claude transcripts.

Black-box web penetration testing automation framework for AI Agents

Gasous Absorption Transmissions at Instrument Averaged Bands

Start your Claude session refresh early to avoid mid-work interruptions

Acceldata LLM observability SDK

Open-source self-healing runtime for Python: RAG + OpenAI-compatible LLM + unified diff patches

Kodemeio LiteLLM CLI — manage LiteLLM proxy instances

Kodemeio Claude Code CLI — manage local and remote Claude Code environments

Proxy server converting between OpenAI Responses API and Chat Completions API

Zero-dependency PII + quality + noise audit for LLM datasets (TR/EU/US)

SIFT - Selective Intelligence Filtering Transformer