ai-plugin-marketplace/template
A single marketplace repo that works with claude, cursor, kiro, gemini and agent skills
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 ai-plugin-marketplace/template/agents ./rig-template/agents $ npx degit ai-plugin-marketplace/template/skills ./rig-template/skills $ npx degit ai-plugin-marketplace/template/hooks ./rig-template/hooks
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 ai-plugin-marketplace/template/plugins/skill-evaluator/skills/evaluate-skill .claude/skills/evaluate-skill $ curl -fsSL --create-dirs -o .claude/agents/experimenter.md https://raw.githubusercontent.com/ai-plugin-marketplace/template/main/agents/experimenter.md $ curl -fsSL --create-dirs -o .claude/agents/test-subject.md https://raw.githubusercontent.com/ai-plugin-marketplace/template/main/agents/test-subject.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 *)"
]
}
} Skills (1)
Subagents (4)
| experimenter model: opus | Orchestrates blind skill evaluation across model tiers |
| test-subject model: sonnet | Blind agent that executes a skill and produces output without knowledge of expected outcomes |
| experimenter | Orchestrates blind skill evaluation across model tiers |
| test-subject | Blind agent that executes a skill and produces output without knowledge of expected outcomes |
Kiro (0 steering)
How Kiro files are scored: methodology.
Similar rigs
edonadei/caliper
Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Claude Code, Codex, Pi, and Hermes.
Minimalist 821 tok · · Q0
EJRyan89/coding-agent-skills
Portable agent skills with a guarded deployer for Claude Code, Codex, and GitHub Copilot
Skill Collector 9.4k tok · · Q25
grimaldost/craft-collection
A Claude Code plugin marketplace that codifies engineering craft: disciplined Python and data-engineering practice alongside deliberate session-knowledge workflows, packaged as reusable skills.
Skill Collector 8.9k tok · · Q3
hassan-mohiddin/freeflow
Feedback-based control system for coding agents
Skill Collector 4.6k tok · · Q5