cglab-public

Agenfk Deep — Productivity skill for Claude Code

Productivity community

Run a task using full Multi-Agent Orchestration (Deep Mode).

How to install Agenfk Deep

Installs to ~/.claude/skills/cglab-public-agenfk-agenfk-deep/SKILL.md

Terminal
mkdir -p ~/.claude/skills/cglab-public-agenfk-agenfk-deep && curl -fsSL https://raw.githubusercontent.com/cglab-public/agenfk/HEAD/commands/agenfk-deep.md -o ~/.claude/skills/cglab-public-agenfk-agenfk-deep/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Agenfk Deep does


description: Run a task using full Multi-Agent Orchestration (Deep Mode)

Use the `agenfk` CLI for all workflow operations (CLI-only is the default; read with `--json` for machine-readable output). If `mcp__agenfk__*` tools are present (installed with `--with-mcp`), the equivalent MCP tool is interchangeable.

Load the `agenfk` skill. Run its Initialization protocol if needed.

**Clean start from main** — Before starting work:

  • Run git status — if the working tree has uncommitted or

Alternatives in Productivity

  • Multi Aider Sub Agent — Run a multi aider_ai_code call with a sub agent call to fulfill the following tasks back to back in the most s 295 ★
  • Meridian — Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp 143 ★
  • Hybrid Auto — Generate PRD from task description and enter review mode 123 ★

Full documentation available on GitHub

View Source Repository