Interactive Claude Code skills, hooks, and CLI utilities from cortex-command for day-to-day development workflows
Manage project backlog items as individual markdown files with YAML frontmatter. Use when user says "/cortex-core:backlog", "backlog add", "backlog list", "backlog pick", "add to backlog", "show backlog", "archive backlog item", "what's ready", "pick a backlog item", or asks to create/view/manage/select backlog items.
Create git commits with consistent, well-formatted messages. Use when user says "commit", "/cortex-core:commit", "make a commit", "commit these changes", or asks to save/checkpoint their work as a git commit.
Dispatches parallel reviewer agents — each focused on a single challenge angle — then synthesizes findings with an Opus agent to deeply challenge a plan, spec, or research artifact from multiple angles before you commit. Domain context from project requirements is injected so reviewers can surface domain-specific failure modes even when the artifact doesn't mention them. Use when the user says "critical review", "pressure test", "adversarial review", "pre-commit challenge", "deeply question", or "challenge from multiple angles". More thorough than a single sequential pass because parallel agents remove anchoring bias and produce deeper per-angle coverage. Also auto-triggers in the lifecycle for Complex + medium/high/critical features after plan approval.
Development entry point that analyzes requests and routes to the appropriate workflow. Use when user says "/cortex-core:dev", "what should I work on", "start working on", "dev hub", "where do I start", "next task", "what's next", or describes a feature without naming a specific skill.
Systematic 4-phase debugging for skills, hooks, lifecycle, and overnight runner issues. Use when: "debug this", "fix this bug", "why is this failing", "investigate this error", "make this test pass", "why isn't this triggering", "skill not working", "hook not running", "lifecycle bug", "overnight runner stall", "diagnose this", "diagnose", or any unexpected behavior in the agentic layer components. Finds root cause, fixes, and verifies with a structured loop.
Executes bash commands
Hook triggers when Bash tool is used
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.
Cortex Command is an AI workflow framework for Claude Code built on a single insight: autonomous execution is only as good as the specification that precedes it.
The front half of the lifecycle is human-driven — discovery maps the problem space, refine clarifies scope, and lifecycle drives features through research, spec, plan, implement, and review. Once scope is genuinely clear, run /cortex-core:lifecycle for interactive development or queue refined items for /overnight and wake up to a morning report with PRs ready to review. For a visual of the full pipeline, see docs/agentic-layer.md.
# 1. Install the cortex CLI (bootstrap installs `uv` first if missing)
curl -fsSL https://raw.githubusercontent.com/charleshall888/cortex-command/main/install.sh | sh
# 2. In Claude Code, add the marketplace and install plugins
claude /plugin marketplace add charleshall888/cortex-command
# Recommended to turn on Auto-Update Marketplace Plugins (this will keep CLI auto updated as well)
claude /plugin install cortex-core@cortex-command # Base skills + hooks
claude /plugin install cortex-overnight@cortex-command # OPTIONAL - autonomous overnight runs
# 3. OPTIONAL - In each project where you want cortex active.
# Validation rules, settings, demo-commands, xetc...
cd <your-project>
cortex init
Full Setup GuideSetup guide.
| Plugin | Description |
|---|---|
| cortex-core | REQUIRED - Interactive Claude Code skills, hooks, and CLI utilities from cortex-command for day-to-day development workflows |
| cortex-overnight | Integrates the cortex MCP server and overnight skill runner hooks to drive autonomous lifecycle execution |
| android-dev-extras | Android development skills vendored from Google's Android Skills (Apache 2.0): R8 analyzer, edge-to-edge migration, and Android CLI orchestration |
| cortex-dev-extras | Optional assortment of additional skills |
| cortex-pr-review | Multi-agent GitHub pull request review pipeline for Claude Code. |
| cortex-ui-extras | EXPERIMENTAL - UI design skills for Claude Code interactive workflows |
| Guide | Covers |
|---|---|
docs/agentic-layer.md | Full skill and hook inventory, workflow diagrams, lifecycle phase map |
docs/setup.md | Installation, plugins, customization |
docs/setup.md#authentication | Authentication setup (API key vs. OAuth token) |
docs/setup.md#upgrade--maintenance | Upgrade & maintenance (CLI reinstall, plugin update, foot-guns) |
docs/overnight.md | Autonomous overnight runner -- planning, execution, deferral, morning review |
docs/dashboard.md | Web dashboard for monitoring overnight sessions |
docs/backlog.md | Backlog YAML schema, readiness gates, overnight eligibility |
docs/interactive-phases.md | What to expect at each lifecycle phase -- questions, artifacts, flow |
docs/skills-reference.md | Per-skill detailed reference |
npx claudepluginhub charleshall888/cortex-command --plugin cortex-coreMulti-agent GitHub pull request review pipeline for Claude Code
No description provided.
No description provided.
Experimental UI design skills for Claude Code interactive workflows
Overnight skill runner hooks that integrate with the cortex CLI on PATH and the cortex-core plugin to drive autonomous lifecycle execution
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
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
Memory compression system for Claude Code - persist context across sessions
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.