agentrigs
+ submit rig
~ / rigs / getappz / agentflare

getappz/agentflare

Run AI coding agents efficiently, and coordinate more than one of them. Zero fluff, zero runtime deps.

↗ GitHub ★ 2 Apache-2.0 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
~3.4k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit getappz/agentflare/.claude ./rig-agentflare  # 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 getappz/agentflare/.claude/skills/algorithm-pseudocode-design .claude/skills/algorithm-pseudocode-design
$ npx degit getappz/agentflare/.claude/skills/brainstorming .claude/skills/brainstorming
$ npx degit getappz/agentflare/.claude/skills/openapi-documentation .claude/skills/openapi-documentation
$ npx degit getappz/agentflare/.claude/skills/pm .claude/skills/pm
$ npx degit getappz/agentflare/.claude/skills/requirements-specification .claude/skills/requirements-specification
$ npx degit getappz/agentflare/.claude/skills/system-architecture-design .claude/skills/system-architecture-design
$ npx degit getappz/agentflare/.claude/skills/systematic-debugging .claude/skills/systematic-debugging

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)

algorithm-pseudocode-designbrainstormingopenapi-documentationpmrequirements-specificationsystem-architecture-designsystematic-debugging

Hooks (1)

eventmatcherruns
SessionStart*"$CLAUDE_PROJECT_DIR"/.claude/hooks/session-start.sh

Slash commands (1)

/pm

Similar rigs

ingeun92/claude-code-configs
—
★ 1 setup Claude Code 7 skills 7d ago
Pragmatist 468 tok ·
nicolasaudran/claude-dotfiles
—
★ 0 setup Claude Code 7 skills 1 hooks 4mo ago
Pragmatist 320 tok ·
echoVic/boss-skill
Boss Skill - BMAD 全自动研发流水线（多 Agent 编排）
★ 563 project Claude Code 1 skills 12 hooks 5d ago
Automator 11 tok ·
handsongice/vibe-rules
跨 coding agent（Claude <redacted> Harness 等）共用的 vibecoding 规范库，一次接入全工具生效，支持 macOS/Linux/Windows
★ 1 project Codex 10 skills 26d ago
Skill Collector 446 tok ·
copied ✓