ESchuderer/BenchKeeper
BenchKeeper keeps your AI coding agents' workbench in order: Claude Code or Codex runs its skills to install and check rules, skills and tools at pinned versions, machine-wide and per repository.
field: unknown workflow: DocsPR / code reviewTesting & TDDFrontend & designSecurity review runs claude in CI
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~7.1k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
$ git clone --depth 1 https://github.com/ESchuderer/BenchKeeper 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 <redacted>.mantine/skills/mantine-family .claude/skills/mantine-family $ npx degit <redacted>.mantine/skills/mantine-form .claude/skills/mantine-form $ npx degit <redacted> .claude/skills/ask $ npx degit <redacted>-repos .claude/skills/maintaining-repos $ npx degit <redacted>-benchkeeper .claude/skills/operating-benchkeeper $ npx degit <redacted>-projects .claude/skills/orchestrating-projects $ npx degit <redacted> .claude/skills/questions $ npx degit <redacted>-rules .claude/skills/reviewing-rules $ npx degit <redacted>-up-projects .claude/skills/setting-up-projects $ npx degit <redacted> .claude/skills/tier $ npx degit <redacted> .claude/skills/workflow
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 |
|---|---|---|
| playwright | local / custom | 2.5k |
| mantine | local / custom | 2.5k |
Skills (11)
Similar rigs
eikelandin/BenchKeeper
BenchKeeper keeps your AI coding agents' workbench in order: Claude Code or Codex runs its skills to install and check rules, skills and tools at pinned versions, machine-wide and per repository.
Skill Collector 1.8k tok · · Q8
vuhuucuong/dotfiles
My Neovim config and relevant stuff
Pragmatist 3.9k tok · · Q15
Dhananjay625/dev-workflow
Plan-first workflow for AI coding agents: cross-session memory via a project changelog, self-assembling domain teams, and tier-calibrated code minimalism. Ships as a Claude Code plugin, a Codex plugin, and a tool-agnostic AGENTS.md.
Pragmatist 2.6k tok · · Q0
ethanhq/cc-fleet
🚢 Run Claude Code's ⚙️ Dynamic Workflows, 👥 Agent Teams & ⚡ Subagents on any third-party model — DeepSeek · GLM · Kimi · Qwen … or your Codex subscription. No Anthropic subscription needed. | 🚢 让 Claude Code 的 ⚙️ Dynamic Workflow、👥 Agent Te
Pragmatist 2.7k tok · · Q3