One of each, then stop

Start with one CLAUDE.md, one MCP, one hook, one skill. Lessons after 4 months of Claude Code.

Share on 𝕏 ↗ Compare with… Read the source ↗

what to steal

Ship with one CLAUDE.md, one MCP, one hook, one skill. Add the second only when the first hurts.

Our takeaway from the source, not a quote.

Drawn from this card's sourced fields. Amber = older model named by the source. Rose = cut or replaced.

okhlopkov-one-of-each.toml

# Start with one CLAUDE.md, one MCP, one hook, one skill
# source: https://okhlopkov.com/claude-code-setup-mcp-hooks-skills-2026/

[rig]
who     = "Lessons after 4 months of Claude Code"
author  = "Daniil Okhlopkov"
date    = "not stated"

harness = ["Claude Code"]
models  = []

[keep]
  - One short CLAUDE.md
  - One MCP in the narrowest scope
  - One hook
  - One skill
  - Subagents only when needed
[cut]
  - Extra MCPs/skills

thing	status	why (per source)
Extra MCPs/skills	avoided	Add only when needed; keep scope narrow

Source: https://okhlopkov.com/claude-code-setup-mcp-hooks-skills-2026/ · checked 2026-10-14

// similar rigs

~/rigs/paulund-herdr-cli.toml2026-10-05

Three desktop apps out, one terminal multiplexer in

steal → Use one session view for all CLIs instead of one app per harness.

CodexClaude CodeOpenCode Codex / Claude Code /

by Paulund

~/rigs/hboon-one-config-three-agent….toml2026-06-27

One config folder, symlinked into three agents

steal → Keep one AGENTS.md and skills folder; symlink it into every harness.

DroidClaude CodeCodex Per-harness config cop

by Hwee-Boon Yar

~/rigs/tartrau-lean-claude-md.tomlundated

CLAUDE.md under 30 lines, detail pushed to path-scoped rules

steal → Keep the always-on file tiny and scope everything else by path.

Claude Code 15 skills

by Thomas Tartrau