llm-context
The portable layer: agent rules, personal context, tool adapters, enforcement hooks, skills, and the brief-to-handoff workflow shared across Claude Code, Codex, and the repos that publish selected content.
/lib
A personal reference hub — the context, rules, and skills that steer how I work with AI tools. The pages below mirror the parts worth keeping close; the source repositories hold the system around them.
The mirrored documents here are generated from llm-context
rather than written on this site.
Tooling
llm-context is public. workstation remains private
by design; GitHub returns a 404 unless you are signed in with access.
workstation
The machine layer: a reproducible Apple Silicon macOS setup with
declarative tooling, per-project runtimes, and security boundaries for
working across multiple client environments. It installs
llm-context as part of a new-machine bootstrap.
Personal Context
personal-context
Who I am and what I'm focused on — the bio my tools load.
voice-and-style
How my writing should read — the full voice, phrase library, and formatting rules.
Global Agent Rules
agent-rules-behavioral
How I work: think first, keep it simple, surgical changes, goal-driven execution, branch before building.
agent-rules-communication
The condensed writing rules — plain language, options with tradeoffs, tone, formatting.
agent-rules-handoff
Where briefs and handoffs live, and how work routes between tools and people.
Skills
Skill library
Reusable engineering, product, security, and compliance workflows for AI coding tools.