By brent-hoover
Guides Claude through problem → design → plan documentation workflow for new features
Personal Claude Code plugin pack. Skills, commands, and hooks for Brent's workflow.
Guides Claude through the full problem → design → plan documentation workflow for a new
feature. Four-phase state machine with approval gates. Claude generates content from targeted
questions; you review and approve each doc before advancing.
Trigger: Say "start a feature", "new feature", or /start-feature [slug].
Output: problem.md, design.md (unless trivial), plan.md in your project's doc
directory.
Templates included: problem, design, plan, deferred, completed.
git clone https://github.com/brent-hoover/caderon-pack ~/path/to/caderon-pack
claude plugins marketplace add ~/path/to/caderon-pack
claude plugins install caderon-pack
Restart Claude Code to activate.
Add to ~/.local/share/chezmoi/.chezmoiexternal.toml:
[".claude/plugins/caderon-pack"]
type = "git-repo"
url = "https://github.com/brent-hoover/caderon-pack.git"
refreshPeriod = "168h"
Then register and install once per machine:
chezmoi apply
claude plugins marketplace add ~/.claude/plugins/caderon-pack
claude plugins install caderon-pack
The start-feature skill auto-detects your project's doc root from CLAUDE.md:
feature-work/ convention → writes to feature-work/<slug>/docs/<slug>/When a feature is complete, write completed.md then move the directory to
<doc-root>/archived/<slug>/.
npm install -g caderon-pack)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 brent-hoover/caderon-pack --plugin doc-driven-developmentComprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
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
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.