December 7, 2025 · development · ai · workflow · claude-code · cli · tools · resources CLI AI Coding: A Vault of Valuable Things This is a companion post to Developing intuition for CLI-based AI coding — that post is about the understanding; this one is about the tools.
This is what nano-banana thought of this post
What this is
A curated list of repos, configs, and practices that have emerged from a group of people thinking hard about CLI-based AI coding. Not everything here will be right for you, but it’s all been road-tested by people doing real work.
Skills and Workflow Systems
Tool What it does Link superpowers Installable skills for Claude Code—TDD, debugging, planning, pressure tests repo / blog 2389 Research skills fresh-eyes-review, scenario-testing repo claude-commands UserPromptSubmit hook for multi-step workflows repo
Installing superpowers:
/plugin marketplace add obra/superpowers-marketplace
/plugin install superpowers@superpowers-marketplace
Memory and Context
Tool What it does Link episodic-memory Cross-session recall for Claude repo private-journal-mcp Persistent journals with vector search repo
File-based planning pattern
Not a repo—a pattern. Externalize state because context window is unreliable; files aren’t.
project/
├── prompt_plan.md # Current plan, model reads but human controls
├── TODO.md # Task list, can be auto-updated via hooks
├── .scratch/ # Disposable working space
└── CLAUDE.md # Project-specific instructions
CLAUDE.md and Configuration
Example configs
Source Notes Link obra/dotfiles Well-structured with testing section CLAUDE.md harperreed/dotfiles Thorough git/pre-commit guidance CLAUDE.md dbmcco/claude-workspace Modular memory system with imports repo glimpser AGENTS.md pattern example / template
Settings and hooks
Source What’s there Link ryankanno/dotfiles ntfy.sh notifications setup settings.json harperreed/dotfiles Commands and agents commands / agents detour1999/dotfiles Commands collection commands
Git and Parallel Work
Worktrees
Built into git—multiple checkouts from one clone. Essential for running multiple Claude instances.
git worktree add ../feature-branch feature-branch
git worktree list
git worktree remove ../feature-branch
Hooks and Guardrails
Pre-commit hooks (last line of defense)
Tool Language Link pre-commit-hooks General repo pre-commit-rust Rust repo ruff-pre-commit Python linting repo Test script example — gist
Claude Code hooks: docs — shell commands on events like tool calls or session starts.
MCP Servers
MCP What it does Link mcp-obsidian Obsidian vault access repo obsidian-mcp Alternative Obsidian MCP repo vocalize-mcp Voice integration repo StageWhisper Voice to text via accessibility APIs repo zen-mcp-server Multi-model access repo playwright-mcp Browser testing repo mcp-language-server LSP to MCP adapter repo ht-mcp Terminal/screen control repo
Agent Orchestration
Tool What it does Link claude-squad Multiple Claude instances coordination repo claude-swarm Swarm-style agent coordination repo lace Custom agentic coding tool, more hookable than CC repo / prompts issue-cards Agent-friendly issue tracker with PM/dev roles repo botboard / 2389 Agent journaling, “social tokens” site / research
Monitoring and Debugging
Tool What it does Link cc-log-viewer Web viewer for Claude Code logs repo ClaudeStatus Terminal status line (prompt, todos, git) repo ccstatusline Alternative status line repo node-traffic-logger HTTP logging for transcript reconstruction repo ScreenshotForChat Screenshot to clipboard in one key repo
GitHub Actions and CI
Tool What it does Link claude-code-action Trigger Claude from GitHub issues/PRs repo / example github-tdd-template TDD-focused GitHub template repo Codex setup script Tool shims, uv, codebase hints gist
Model Routing and Proxies
Tool What it does Link claude-code-router Route through OpenRouter for other models repo claude-code-proxy Multi-model with judge voting repo
Alternative Interfaces
Tool What it does Link claude-code-webui Web UI for Claude Code repo claude-code.nvim Neovim integration repo Ghostty setup AppleScript for Ghostty + neovim gist
Mobile and Remote
The stack: tmux (persistence) + mosh (handles network changes) + Tailscale (VPN) + Termux (Android)
Voice Tool What it does Link loq Voice input repo whisper-to-input API-based voice input repo dsnote Local voice transcription repo
Project What it is Link pgsqlite Postgres wrapper on SQLite repo gruboros RNN training project repo hyprmon Hyprland monitor management TUI repo tiny-agent Minimal agentic loop (~1KB) repo smallest-agent Even smaller agent example repo
Methodology Posts
Post Link Superpowers methodology (June 2025) blog System prompts comparison blog Anthropic’s internal usage PDF
House Rules
Patterns that aren’t tools but are worth codifying:
Rule Why Plans in files, not in context Context window forgets. Files don’t. Shorter sessions, more often Context rot is real. Clear early and often. Guardrails in code, not in prompts Instructions decay. Pre-commit hooks don’t. Verify, don’t trust Model speaks with same confidence right or wrong. Expect shortcuts Model will find the easy path. Design around it. No mocks in tests Or at least separate TestsWithMocks/ and TestsWithoutMocks/ Give Claude access to the MCP while developing it Makes dev go 5x faster.
Last updated: December 2025
Claude helped me write this post. A lot. But the thinking and tone are mine.
Originally published at dbmcco.github.io .
Back All writing →
Set Earth Inc · Contracts and invoices under this entity · Reply to
b@mcco.us