agentrigs
+ submit rig
~ / rigs / HourglassDigital / hgstack

HourglassDigital/hgstack

The Claude Code stack we use to run an AI-native company. Skills, hooks, rules, and statuslines from 18 months of daily use at Hourglass. Conflict-aware installer never stomps your existing setup.

↗ GitHub ★ 4 MIT updated today project Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~821 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit HourglassDigital/hgstack/skills ./rig-hgstack/skills
$ npx degit HourglassDigital/hgstack/hooks ./rig-hgstack/hooks

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 HourglassDigital/hgstack/skills/codex-review .claude/skills/codex-review
$ npx degit HourglassDigital/hgstack/skills/consume .claude/skills/consume
$ npx degit HourglassDigital/hgstack/skills/hg-eval-gates .claude/skills/hg-eval-gates
$ npx degit HourglassDigital/hgstack/skills/hg-ship .claude/skills/hg-ship
$ npx degit HourglassDigital/hgstack/skills/interview-me .claude/skills/interview-me
$ npx degit HourglassDigital/hgstack/skills/outcome-loop .claude/skills/outcome-loop
$ npx degit HourglassDigital/hgstack/skills/tutor .claude/skills/tutor

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (7)

codex-reviewconsumehg-eval-gateshg-shipinterview-meoutcome-looptutor

Similar rigs

chaseai-yt/claudex-loop
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never gr
★ 1,640 project Claude Code 4 skills 1mo ago
Minimalist 272 tok ·
will-pagane/claude-superdev-harness
Minha config pessoal do Claude Code — CLAUDE.md global, statusline custom, stack de plugins/skills
★ 4 setup Claude Code 5 skills 17d ago
Pragmatist 2.0k tok ·
lil-lon/.claude
🎨 My Claude Code config. Build something interesting and fun.
★ 2 setup Claude Code 6 skills 1 hooks 4mo ago
Fort Knox 839 tok ·
appleboy/skills
Agent Skills Collection
★ 23 collection Claude Code 7 skills 27d ago
Pragmatist 601 tok ·
copied ✓