~ / rigs / syncwin / ai-extender

syncwin/ai-extender

Describe what you want Claude to do, and AI Extender plans, builds, checks, and packages the skill, plugin, or internal tool for you.

↗ GitHub ★ 0 MIT updated 8d ago project Claude CodeCodex Claude plugin
stack: Python
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~3.4k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 8/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ claude mcp add --transport http composio https://connect.composio.dev/mcp
$ npx degit syncwin/ai-extender/.claude ./rig-ai-extender  # 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 --transport http composio https://connect.composio.dev/mcp
$ npx degit syncwin/ai-extender/skills/aix-cleaner .claude/skills/aix-cleaner
$ npx degit syncwin/ai-extender/skills/aix-developer .claude/skills/aix-developer
$ npx degit syncwin/ai-extender/skills/aix-maintainer .claude/skills/aix-maintainer
$ npx degit syncwin/ai-extender/skills/aix-packager .claude/skills/aix-packager
$ npx degit syncwin/ai-extender/skills/aix-planner .claude/skills/aix-planner
$ npx degit syncwin/ai-extender/skills/aix-prompter .claude/skills/aix-prompter
$ npx degit syncwin/ai-extender/skills/aix-reviewer .claude/skills/aix-reviewer
$ npx degit syncwin/ai-extender/skills/aix .claude/skills/aix
$ curl -fsSL --create-dirs -o .claude/agents/claude-comparator.md https://raw.githubusercontent.com/syncwin/ai-extender/main/agents/claude-comparator.md
$ curl -fsSL --create-dirs -o .claude/agents/claude-grader.md https://raw.githubusercontent.com/syncwin/ai-extender/main/agents/claude-grader.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 *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
connect.composio.dev · "composio" remote · remote 2.5k

Skills (8)

Subagents (2)

claude-comparator
model: inherit
Blind-compares two outputs for the same task (labeled A and B) and says which is better and why. Use to compare an extension version against a baseline or a previous version without revealing which is
claude-grader
model: inherit
Grades one extension test run against its assertions and writes grading.json. Use after an eval run finishes, when each assertion needs a pass/fail with quoted evidence.

Similar rigs

copied ✓