agentrigs
+ submit rig
~ / rigs / raulfrk / setforge

raulfrk/setforge

Personal dotfiles for Claude Code + VSCode, managed via dotdrop + Make

↗ GitHub ★ 0 MIT updated today project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~6.1k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit raulfrk/setforge/.claude ./rig-setforge  # 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.

$ npx degit raulfrk/setforge/.claude/skills/enforce-tests .claude/skills/enforce-tests
$ npx degit raulfrk/setforge/.claude/skills/surface-proposals .claude/skills/surface-proposals
$ curl -fsSL --create-dirs -o .claude/agents/design-invariant-reviewer.md https://raw.githubusercontent.com/raulfrk/setforge/main/.claude/agents/design-invariant-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/test-quality-reviewer.md https://raw.githubusercontent.com/raulfrk/setforge/main/.claude/agents/test-quality-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/visual-auditor.md https://raw.githubusercontent.com/raulfrk/setforge/main/.claude/agents/visual-auditor.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": "f=\"$HOME/setforge/scripts/policy_lint_hook.py\"; [ -f \"$f\" ] && python3 \"$f\""
          }
        ]
      }
    ]
  }
}

Skills (2)

enforce-testssurface-proposals

Subagents (3)

design-invariant-reviewer
model: opus
Design-invariant reviewer for setforge UX + safety/provisioner design rules. Use after edits to wizard / TUI / theme code or provisioner / cleanup code to verify adherence to UX-2, UX-5, UX-6, SAFE-9
test-quality-reviewer
model: opus
Test-quality reviewer for setforge. Use after test edits to verify tier placement, audit-and-prune signal (change-detector / over-mocked / tautological / assertion-free / redundant / blessed-snapshot)
visual-auditor
model: sonnet
Runtime UI/visual auditor for setforge's terminal UI. Drives real CLI/TUI flows in the Docker e2e container, captures the full-screen output as a pyte text-grid, and reports visual defects — misalignm

Hooks (1)

eventmatcherruns
PreToolUseBashf="$HOME/setforge/scripts/policy_lint_hook.py"; [ -f "$f" ] && python3 "$f"

Similar rigs

MiguelAxcar/ai-rpi-protocol
Repo-native protocol for AI-assisted coding that enforces a simple discipline: research first, plan second, code last. Drop it into any repository to reduce wrong implementations, cut rewrite cycles, and improve decisions earlier in the wor
★ 28 project Claude CodeCodex 15 agents 7mo ago
Orchestrator 2.3k tok ·
anomalyco/opencode
The open source coding agent.
★ 212k project Codex 2 skills 1d ago
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
★ 155k project CodexCursorCopilot 6 skills 4d ago
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
★ 141k project Claude CodeCodex 1 mcp 3 skills 9d ago
Pragmatist 4.2k tok ·
copied ✓