agentrigs
+ submit rig
~ / rigs / michaelo-ponteski / dotfiles

michaelo-ponteski/dotfiles

Personal dotfiles for macOS setup (zsh, tmux, wezterm, claude code, .config tools)

↗ GitHub ★ 0 no license updated 4mo ago personal setup Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~2.1k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit michaelo-ponteski/dotfiles/home/.claude ./rig-dotfiles  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ curl -fsSL --create-dirs -o .claude/agents/adversarial-planner.md https://raw.githubusercontent.com/michaelo-ponteski/dotfiles/main/home/.claude/agents/adversarial-planner.md
$ curl -fsSL --create-dirs -o .claude/agents/bug-hypothesizer.md https://raw.githubusercontent.com/michaelo-ponteski/dotfiles/main/home/.claude/agents/bug-hypothesizer.md
$ curl -fsSL --create-dirs -o .claude/agents/edit-fanout.md https://raw.githubusercontent.com/michaelo-ponteski/dotfiles/main/home/.claude/agents/edit-fanout.md
$ curl -fsSL --create-dirs -o .claude/agents/ml-paper-digester.md https://raw.githubusercontent.com/michaelo-ponteski/dotfiles/main/home/.claude/agents/ml-paper-digester.md
$ curl -fsSL --create-dirs -o .claude/agents/remote-safety.md https://raw.githubusercontent.com/michaelo-ponteski/dotfiles/main/home/.claude/agents/remote-safety.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "~/.claude/hooks/remote-safety-gate.sh"
          }
        ]
      }
    ]
  }
}

Subagents (5)

adversarial-planner
model: opus
Attack a plan or design to find what's wrong with it before code is written. Use this agent AFTER a plan exists (your own, the built-in Plan agent's output, a design doc, or a proposed architecture) a
bug-hypothesizer
model: opus
For "this is broken and I don't know why" investigations. Use this agent when there's a concrete symptom (failing test, wrong output, exception, perf regression, intermittent flake) and the cause is n
edit-fanout
model: opus
Apply a mechanical-but-semantic change across many files where sed/global-find-replace would be too dumb. Use this agent when the task is "do the same change in N places, but with judgment" — e.g. ren
ml-paper-digester
model: sonnet
Fetch and produce a structured summary of an ML paper, documentation page, or technical writeup from a URL or arXiv ID. Use this agent when the user wants to understand a paper/post without polluting
remote-safety
model: sonnet
Pre-flight safety check before any remote-affecting git/GitHub operation. Use this agent BEFORE running git push, git push --force, gh pr create, gh pr merge, changing remote URLs, or running gh auth.

Hooks (3)

eventmatcherruns
SessionStart*~/.claude/hooks/prune-document-skills.sh
PreToolUseBash~/.claude/hooks/remote-safety-gate.sh
Notification*~/.claude/hooks/notify.sh

Plugins (9)

ui-ux-pro-max@ui-ux-pro-max-skilldocument-skills@anthropic-agent-skillssuperpowers@claude-plugins-officialcode-review@claude-plugins-officialcode-simplifier@claude-plugins-officialplaywright@claude-plugins-officialclaude-md-management@claude-plugins-officialtypescript-lsp@claude-plugins-officialclaude-code-setup@claude-plugins-official

Permissions

deny (0)
—
ask (0)
—
allow (2)
Bash(npx tsc --noEmit *)
Bash(npm run lint *)

Similar rigs

jakubsuplicki/codument
Docs-based guardrails for AI coding workflows: coverage scoring, doc-drift checks, and diff safety review.
★ 48 project Claude CodeCodex 15 skills 5 agents 4d ago
Orchestrator 7.4k tok ·
rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
★ 82.5k project Claude CodeCopilot 12 skills 6 agents 4d ago
Orchestrator 2.6k tok ·
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code
★ 39.6k setup Claude CodeCodex 1 mcp 47 skills 19 agents 5d ago
Orchestrator 14.5k tok ·
alirezarezvani/claude-skills
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, complian
★ 27.9k project Claude CodeGemini CLI 2 mcp 147 skills 32 agents 1mo ago
Orchestrator 48.5k tok ·
copied ✓