qkitzero/kage-bunshin
🥷 AI agents for knowledge work, not code
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 qkitzero/kage-bunshin/.claude ./rig-kage-bunshin # 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 qkitzero/kage-bunshin/.claude/skills/brainstorm .claude/skills/brainstorm $ npx degit qkitzero/kage-bunshin/.claude/skills/evaluate .claude/skills/evaluate $ npx degit qkitzero/kage-bunshin/.claude/skills/learning .claude/skills/learning $ npx degit qkitzero/kage-bunshin/.claude/skills/notebook .claude/skills/notebook $ npx degit qkitzero/kage-bunshin/.claude/skills/plan-project .claude/skills/plan-project
$ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/qkitzero/kage-bunshin/main/.claude/agents/analyst.md $ curl -fsSL --create-dirs -o .claude/agents/ideator.md https://raw.githubusercontent.com/qkitzero/kage-bunshin/main/.claude/agents/ideator.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/qkitzero/kage-bunshin/main/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/qkitzero/kage-bunshin/main/.claude/agents/researcher.md
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 (5)
Subagents (4)
| analyst model: opus | > |
| ideator model: opus | > |
| planner model: opus | > |
| researcher model: opus | > |
Permissions
deny (0)
—
ask (0)
—
allow (4)
WebSearch
WebFetch
Bash(git:*)
Bash(gh:*)
Similar rigs
tylerjkells/claude-dotfiles
—
Pragmatist 579 tok ·
nicodiansk/turboflow
Opinionated engineering pipeline for Claude Code with 10 skills, 5 agents, 2 hooks. Replaces ad-hoc agent sprawl with brainstorm → story → plan → build → review → ship.
Orchestrator 1.9k tok ·
fjerbi/claude-code-arsenal
A tested Claude Code operating system for efficient, reliable, and focused software engineering. Includes global instructions, workflows, rules, and tools designed to minimize wasted tokens, prevent hallucinations and unnecessary loops, enf
YOLO Cowboy 4.0k tok ·
Remus3/Resin-Compute
Genshin Impact wish and pity forecaster on an absorbing Markov chain, with resin budgeting, goal planning and an Enka.Network profile client. Headless-first Python 3.11, stdlib-only at runtime, no game data vendored.
Orchestrator 9.0k tok ·