afaraha8403/balakit
Opinionated, cross-agent rules and skills for AI coding agents — one npx install into Cursor, Claude Code, Codex, OpenCode & Copilot.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit afaraha8403/balakit/.claude ./rig-balakit # 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 afaraha8403/balakit/.agents/skills/agent-ready .claude/skills/agent-ready $ npx degit afaraha8403/balakit/.agents/skills/authoring-skills-and-rules .claude/skills/authoring-skills-and-rules $ npx degit afaraha8403/balakit/.agents/skills/blinded-eval .claude/skills/blinded-eval $ npx degit afaraha8403/balakit/.agents/skills/cloakbrowser-fallback .claude/skills/cloakbrowser-fallback $ npx degit afaraha8403/balakit/.agents/skills/deep-deliberation .claude/skills/deep-deliberation $ npx degit afaraha8403/balakit/.agents/skills/design-rationale .claude/skills/design-rationale $ npx degit afaraha8403/balakit/.agents/skills/dissect .claude/skills/dissect $ npx degit afaraha8403/balakit/.agents/skills/documentation-writer .claude/skills/documentation-writer $ npx degit afaraha8403/balakit/.agents/skills/everything-seo .claude/skills/everything-seo $ npx degit afaraha8403/balakit/.agents/skills/execute .claude/skills/execute $ npx degit afaraha8403/balakit/.agents/skills/generating-app-verify .claude/skills/generating-app-verify $ npx degit afaraha8403/balakit/.agents/skills/inception .claude/skills/inception $ npx degit afaraha8403/balakit/.agents/skills/kit-workflows .claude/skills/kit-workflows $ npx degit afaraha8403/balakit/.agents/skills/marketing-psychology .claude/skills/marketing-psychology $ npx degit afaraha8403/balakit/.agents/skills/media-gen .claude/skills/media-gen $ npx degit afaraha8403/balakit/.agents/skills/nlm-skill .claude/skills/nlm-skill $ npx degit afaraha8403/balakit/.agents/skills/opinion .claude/skills/opinion $ npx degit afaraha8403/balakit/.agents/skills/proving-change-safety .claude/skills/proving-change-safety $ npx degit afaraha8403/balakit/.agents/skills/refreshing-app-verify .claude/skills/refreshing-app-verify $ npx degit afaraha8403/balakit/.agents/skills/release-deploy .claude/skills/release-deploy $ npx degit afaraha8403/balakit/.agents/skills/seo-audit .claude/skills/seo-audit $ npx degit afaraha8403/balakit/.agents/skills/startup-marketing-brain .claude/skills/startup-marketing-brain $ npx degit afaraha8403/balakit/.agents/skills/subsystem-walkthrough .claude/skills/subsystem-walkthrough $ npx degit afaraha8403/balakit/.agents/skills/unmatched-workflow .claude/skills/unmatched-workflow
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 (24)
agent-readyauthoring-skills-and-rulesblinded-evalcloakbrowser-fallbackdeep-deliberationdesign-rationaledissectdocumentation-writereverything-seoexecutegenerating-app-verifyinceptionkit-workflowsmarketing-psychologymedia-gennlm-skillopinionproving-change-safetyrefreshing-app-verifyrelease-deployseo-auditstartup-marketing-brainsubsystem-walkthroughunmatched-workflow
Cursor rules (6)
base · alwayschangelog · alwayscomments · alwaysrelease · alwaysseo-ai-searchtesting · always
Similar rigs
josstei/maestro-orchestrate
Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools
Skill Collector 7.5k tok ·
tickets-forge-dev/loop-lang
An open, natural-language DSL for self-correcting AI coding loops — say what an AI coding agent should build and how to verify it in plain English, and it loops until the check passes. Runs in Claude Code, Cursor, and Copilot.
Pragmatist 5.4k tok ·
DesiRichDev/Claude-Cowork-Linkedin-X
Social content agent for LinkedIn and X. Drop in your brand config, research signals, write platform-native posts, review quality, push to Supabase. Built on Claude Code.
Pragmatist 505 tok ·
TheCraigHewitt/seomachine
A specialized Claude Code workspace for creating long-form, SEO-optimized blog content for any business. This system helps you research, write, analyze, and optimize content that ranks well and serves your target audience.
Orchestrator 3.5k tok ·