#llm-agents

Autoharness

Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes th...

Unified Code Review

Risk-first agent skill for PR/branch review: blast radius, agent-authored checks, call-graph pincer, structural bar.

WIT Skill

Writing is thinking! WIT provides skills for scientific thinking and writing!

Cicada

Cicada — Security Audit & Fix Skill for LLM coding agents (16 domains, cross-framework)

SkillHone

Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every d...

MCP Capability Ledger

Infer least-privilege MCP tool policies from agent traces

Bitbucket MCP

Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs

Dev Kit MCP Server

Agent development tool-kit

Yesmem

Persistent memory system for Coding Agents (Claude, Opencode, Codex), infinite context, learning extraction, persona modeling and so much m...

Theodosia

Put an AI agent on rails: mount a Burr state machine as an MCP server so the agent can only take the next allowed step, with every step reco...

LLM Council

The LLM Council works together to answer your hardest questions