kirillonishuk/hangar
Native macOS workspace for AI coding agents: Claude Code and Codex in Ghostty terminal tabs, with sessions, Git, diffs and a TypeScript-aware editor.
stack: Swift
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit kirillonishuk/hangar/.claude ./rig-hangar # 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 kirillonishuk/hangar/.claude/skills/hangar-code .claude/skills/hangar-code $ npx degit kirillonishuk/hangar/.claude/skills/hangar-commit .claude/skills/hangar-commit $ npx degit kirillonishuk/hangar/.claude/skills/hangar-release .claude/skills/hangar-release $ npx degit kirillonishuk/hangar/.claude/skills/hangar-test .claude/skills/hangar-test
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/kirillonishuk/hangar/main/.claude/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/kirillonishuk/hangar/main/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/kirillonishuk/hangar/main/.claude/agents/qa.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/kirillonishuk/hangar/main/.claude/agents/reviewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (4)
Subagents (4)
| implementer | Executes one well-specified Hangar task end to end (code, tests, docs, commit) in the given branch/worktree and reports briefly. Use for every implementation or fix task. |
| orchestrator | Main-thread coordinator for Hangar work. Plans, dispatches implementer/reviewer/qa subagents, decides, and talks to the owner. Never writes code itself. |
| qa model: sonnet | Live UI pass of a Hangar branch in an isolated DEBUG build — drives the app through the debug channel, captures screenshots to /tmp, reports broken or ugly UI. Use for any change visible in the UI. |
| reviewer model: sonnet | Independent code review of a Hangar change (branch or commit range) against the spec, decisions and AGENTS.md. Runs the tests. Read-only. Use after every implementer task and before any merge. |
Similar rigs
IntuitivePhella/AI-PhellOS
Portable AI development workflow template and CLI for spec-driven, test-aware software delivery with Codex, Claude Code, and other coding agents.
Orchestrator 3.1k tok · · Q31
Saba-Var/claude-ward
A read-only tripwire that watches Claude Code's local config and reports suspicious changes.
Pragmatist 1.8k tok · · Q21
yopazerbot/brieltje
Smetlede and Briel (Lede, Belgium) in 3D: a walkable village in the browser, alone or with up to 16 friends. Explore, Paintball, Action, and endless waves of Zombies. Three.js and Blender, made with Claude Code and OpenAI Codex..
Pragmatist 4.7k tok · · Q8
0xT4sty/claude-code-dotfiles
—
Pragmatist 979 tok · · Q0