rbaskam/PRism
PRism: review GitHub pull requests across all your repositories with Claude Code. A PR dashboard with team review requests, AI code review, inline findings and fixes in isolated worktrees. Desktop app for macOS and Windows.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add laravel-boost -- php artisan boost:mcp $ npx degit rbaskam/PRism/.claude ./rig-prism # 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 laravel-boost -- php artisan boost:mcp $ npx degit rbaskam/PRism/.ai/skills/nativephp-desktop .claude/skills/nativephp-desktop $ npx degit rbaskam/PRism/.ai/skills/shipping-changes .claude/skills/shipping-changes $ npx degit rbaskam/PRism/.claude/skills/inertia-vue-development .claude/skills/inertia-vue-development $ npx degit rbaskam/PRism/.claude/skills/infer-conventions .claude/skills/infer-conventions $ npx degit rbaskam/PRism/.claude/skills/laravel-best-practices .claude/skills/laravel-best-practices $ npx degit rbaskam/PRism/.claude/skills/tailwindcss-development .claude/skills/tailwindcss-development $ npx degit rbaskam/PRism/.claude/skills/testing-best-practices .claude/skills/testing-best-practices
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)
| server | source | est. tokens |
|---|---|---|
| php · "laravel-boost" | binary | 2.5k |
Skills (7)
Similar rigs
nickture/ai-native-laravel
How an AI-native Laravel project keeps what its agents need to know: Foundation, Laravel Boost and CLAUDE.md, design and text rules by topic, skills, plans and a debt registry. The knowledge layer of Overy, without the code.
Pragmatist 12.0k tok · · Q3
muhammedozalp/laravel-agent-team-template
Production-grade Laravel 13 + React starter kit template developed by a 4-agent Claude Code team — Docker, PostgreSQL 17, Fortify auth (hardened), TDD, full testing pyramid incl. e2e/a11y/cross-browser, token-optimized AI workflow
Automator 8.2k tok · · Q34
saifulabidin/BeatifulPHPLaravel
Agent Skills teaching AI coding agents to write, review, and port idiomatic PHP (8.3 - 8.5) and Laravel 13.x, plus drop-in Pint & Larastan configs. Works with Claude Code, Cursor, Copilot, and Antigravity.
Minimalist 892 tok · · Q0
robiparvez/claude-code-guidelines
A personal, evidence-based reference for how Claude Code is used day-to-day: real skills, workflow habits, and global config, organized by Laravel, Angular, React, and Java/Spring Boot. No generic advice—every entry traces to a real skill f
YOLO Cowboy 1.3k tok · · Q19