Bradliebs/ollama-agent-harness

debugging

Systematic debugging for the Ollama Agent Harness — reproduce, localize, reduce, fix, guard

git-workflow

Git workflow for the Ollama Agent Harness — atomic commits, small changes, safe history

security-hardening

Security hardening for the Ollama Agent Harness — input validation, command injection, secrets, deny-first review

mcp-builder

Build a new MCP (Model Context Protocol) server from scratch — a stdio program that exposes tools to AI agents. Use when the user wants to wrap an API, CLI, or internal service as an MCP server the harness (or Claude Desktop, Cursor, etc.) can load. Adapted…

harness-conventions

Project conventions for the Ollama Agent Harness — architectural patterns borrowed from the Claude Code paper

home-iq

Passively get to know the user over time — distill durable facts about who they are, what they work on, and how they like to be helped from conversation history into USER.md and memory. The home-user analog of Microsoft Work IQ's implicit-memory layer. Use…

second-brain

Build and maintain a Karpathy-style LLM-maintained personal wiki (a "Second Brain") as plain markdown the user owns. Use when the user wants to set up a second brain, capture/ingest a source into their notes, ask their knowledge base a question, file…

research

Evidence-first research — gathers sources on a topic, synthesises findings, and cites every claim. Marks what could not be verified instead of guessing.

code-review

Code review skill for the Ollama Agent Harness — enforces architectural conventions from the Claude Code paper

copilotforge-plan-executor

Autonomous plan execution — reads IMPLEMENTATION_PLAN.md, picks the next task, implements it, validates, commits, and repeats

copilotforge-planner

Guided wizard that scaffolds Copilot skills, agents, memory, and cookbook recipes into any repo from a plain-English project description

shopping-assistant

Supervised shopping assistant — browses stores, compares prices, builds baskets, but ALWAYS requires human approval before checkout

testing

Testing conventions for the Ollama Agent Harness using Jest