ValentinFigue/aether
Checkpoints for coding agents: critique the plan, review the diff, block the unreviewed push.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~8.7k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add bonsai-py -- uv run --directory py bonsai-py $ npx degit ValentinFigue/aether/plugins/cairn/.claude ./rig-aether # 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.
$ claude mcp add bonsai-py -- uv run --directory py bonsai-py $ npx degit <redacted>-first .claude/skills/bonsai-first $ npx degit ValentinFigue/aether/plugins/temper/skills/sync-docs .claude/skills/sync-docs
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 *)"
]
}
} MCP servers (2)
| server | source | est. tokens |
|---|---|---|
| py · "bonsai-py" | pypi | 2.5k |
| bonsai-ts | local / custom | 2.5k |
Skills (2)
Slash commands (10)
/draft-changelog/draft-commit/draft-pr/draft-summary/sync-main/critique-diff/critique-pr/interview-pr/draft-config/critique-plan
Similar rigs
enerage/vibespace
One taskbar app per repo — file tree + Monaco preview + Claude Code agent terminals that never die
Pragmatist 14.4k tok · · Q3
synaptic-ai-consulting/AAMAD
A Context Engineering Framework for AI-Assisted Multi Agent Applications Development
Pragmatist 7.9k tok · · Q0
aikazu/kelola-router
Local-first API router for MiniMax + Kiro (AWS CodeWhisperer / Amazon Q) upstreams — OpenAI & Anthropic compatible, multi-account fallback, switchable Kiro IDE/CLI persona, RTK + Caveman compression, built-in dashboard (Hono + SQLite + Prea
Pragmatist 5.2k tok · · Q20
sdolard/awesome-claude-config
Portable, stack-agnostic methodology guidelines for building/constraining UI, meant to be integrated into a Claude Code configuration (rules/hooks/skills/agents).
Pragmatist 963 tok · · Q0