By gejustin
Interview-driven authoring of AI context (skills, AGENTS.md guides, guardrail specs) against a portable context framework, with evidence attached
Gary's personal agent workflows, packaged as portable plugins. Claude Code consumes .claude-plugin/marketplace.json, Cursor consumes .cursor-plugin/marketplace.json, and Codex consumes .agents/plugins/marketplace.json.
| Plugin | Claude Code | Cursor | Codex | Status | Purpose |
|---|---|---|---|---|---|
context-framework | Yes | IDE only | Yes | WIP | Standardize how in-repo AI context is created and consumed, tool-agnostic. |
core | Yes | IDE only | Yes | Ready | Portable engineering-discipline skills. Currently: autoresearch. |
# Add the marketplace from a local clone
/plugin marketplace add .
# Or add it directly from GitHub
/plugin marketplace add [email protected]:gejustin/agent-development-kit.git
# Install a plugin
/plugin install context-framework@agent-development-kit
git clone [email protected]:gejustin/agent-development-kit.git
mkdir -p ~/.cursor/plugins/local
ln -s "$(pwd)/agent-development-kit/plugins/context-framework" ~/.cursor/plugins/local/context-framework
Then Developer: Reload Window in Cursor. git pull picks up updates — no reinstall.
The Cursor CLI (agent / cursor-agent) does not read this path yet. CLI support pending Cursor unifying plugin resolution between IDE and CLI.
codex plugin marketplace add gejustin/agent-development-kit
Then open /plugins and install context-framework.
MIT.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub gejustin/agent-development-kit --plugin context-frameworkPortable engineering-discipline skills — autoresearch and more to come
Manage HAI annotation pipelines — pull metrics from BigQuery, diagnose pipeline issues, analyze ramp plans, and manage fellows. Built for operators (SPLs/SPAs) who run data annotation projects for AI labs.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Next.js development expertise with skills for App Router, Server Components, Route Handlers, Server Actions, and authentication patterns
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Efficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domains