sameerhimati/claude-code-kit
My Claude Code setup: skills, agents, hooks, and rules.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit sameerhimati/claude-code-kit/agents ./rig-claude-code-kit/agents $ npx degit sameerhimati/claude-code-kit/skills ./rig-claude-code-kit/skills
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 sameerhimati/claude-code-kit/legacy/skills/airtable-ops .claude/skills/airtable-ops $ npx degit sameerhimati/claude-code-kit/legacy/skills/cloudflare-setup .claude/skills/cloudflare-setup $ npx degit sameerhimati/claude-code-kit/legacy/skills/code-standards .claude/skills/code-standards $ npx degit sameerhimati/claude-code-kit/legacy/skills/commit-conventions .claude/skills/commit-conventions $ npx degit sameerhimati/claude-code-kit/legacy/skills/data-pipeline .claude/skills/data-pipeline $ npx degit sameerhimati/claude-code-kit/legacy/skills/design-philosophy .claude/skills/design-philosophy $ npx degit sameerhimati/claude-code-kit/legacy/skills/doc-parser .claude/skills/doc-parser $ npx degit sameerhimati/claude-code-kit/legacy/skills/ml-model .claude/skills/ml-model $ npx degit sameerhimati/claude-code-kit/legacy/skills/nextjs-patterns .claude/skills/nextjs-patterns $ npx degit sameerhimati/claude-code-kit/legacy/skills/oauth-setup .claude/skills/oauth-setup $ npx degit sameerhimati/claude-code-kit/legacy/skills/python-fastapi-patterns .claude/skills/python-fastapi-patterns $ npx degit sameerhimati/claude-code-kit/legacy/skills/railway-deploy .claude/skills/railway-deploy $ npx degit sameerhimati/claude-code-kit/legacy/skills/scraper-auth .claude/skills/scraper-auth $ npx degit sameerhimati/claude-code-kit/legacy/skills/techdebt-scanner .claude/skills/techdebt-scanner $ npx degit sameerhimati/claude-code-kit/skills/autoloop .claude/skills/autoloop $ npx degit sameerhimati/claude-code-kit/skills/claude-api .claude/skills/claude-api $ npx degit sameerhimati/claude-code-kit/skills/compile .claude/skills/compile $ npx degit sameerhimati/claude-code-kit/skills/config-audit .claude/skills/config-audit $ npx degit sameerhimati/claude-code-kit/skills/deploy .claude/skills/deploy $ npx degit sameerhimati/claude-code-kit/skills/design-review .claude/skills/design-review $ npx degit sameerhimati/claude-code-kit/skills/deslop .claude/skills/deslop $ npx degit sameerhimati/claude-code-kit/skills/feature-flow .claude/skills/feature-flow $ npx degit sameerhimati/claude-code-kit/skills/glow-up .claude/skills/glow-up $ npx degit sameerhimati/claude-code-kit/skills/hallmark .claude/skills/hallmark $ npx degit sameerhimati/claude-code-kit/skills/investigate .claude/skills/investigate $ npx degit sameerhimati/claude-code-kit/skills/learn .claude/skills/learn $ npx degit sameerhimati/claude-code-kit/skills/lint .claude/skills/lint $ npx degit sameerhimati/claude-code-kit/skills/office-hours .claude/skills/office-hours $ npx degit sameerhimati/claude-code-kit/skills/oss .claude/skills/oss $ npx degit sameerhimati/claude-code-kit/skills/paper .claude/skills/paper $ npx degit sameerhimati/claude-code-kit/skills/plan-ceo-review .claude/skills/plan-ceo-review $ npx degit sameerhimati/claude-code-kit/skills/plan-design-review .claude/skills/plan-design-review $ npx degit sameerhimati/claude-code-kit/skills/plan-devex-review .claude/skills/plan-devex-review $ npx degit sameerhimati/claude-code-kit/skills/plan-eng-review .claude/skills/plan-eng-review $ npx degit sameerhimati/claude-code-kit/skills/prototype .claude/skills/prototype $ npx degit sameerhimati/claude-code-kit/skills/qa .claude/skills/qa $ npx degit sameerhimati/claude-code-kit/skills/research .claude/skills/research $ npx degit sameerhimati/claude-code-kit/skills/session-handoff .claude/skills/session-handoff $ npx degit sameerhimati/claude-code-kit/skills/session-kickoff .claude/skills/session-kickoff $ npx degit sameerhimati/claude-code-kit/skills/think .claude/skills/think
$ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/analyst.md $ curl -fsSL --create-dirs -o .claude/agents/config-auditor.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/config-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/critic.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/critic.md $ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/doc-updater.md $ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/explorer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/security-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/security-scanner.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/security-scanner.md $ curl -fsSL --create-dirs -o .claude/agents/skill-author.md https://raw.githubusercontent.com/sameerhimati/claude-code-kit/main/agents/skill-author.md
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 (43)
airtable-opscloudflare-setupcode-standardscommit-conventionsdata-pipelinedesign-philosophydoc-parserml-modelnextjs-patternsoauth-setuppython-fastapi-patternsrailway-deployscraper-authtechdebt-scannerautoloopclaude-apicompileconfig-auditdeploydesign-reviewdeslopfeature-flowglow-uphallmarkinvestigatelearnlintoffice-hoursosspaperplan-ceo-reviewplan-design-reviewplan-devex-reviewplan-eng-reviewprototypeqaresearchsession-handoffsession-kickoffthinkuse-railwayux-auditverify
Subagents (11)
| analyst model: sonnet | Reviews marketing metrics and performance data. Suggests optimizations based on what the numbers say. |
| config-auditor model: sonnet | Audits the ~/.claude configuration for drift, bloat, and breakage. Read-only — reports findings and recommended actions, does not change files. Backs the /config-audit skill. |
| critic model: opus | Adversarial reviewer. Attacks marketing copy from the perspective of skeptical buyers, competitors, and distracted audiences. |
| doc-updater model: haiku | Updates project docs after feature completion. |
| explorer model: sonnet | Read-only codebase mapper tuned for Sameer's stacks (Python/DuckDB/FastAPI; Next.js/Tailwind/Prisma). Use for broad fan-out searches across many files where you need a condensed map, not file dumps. R |
| planner model: opus | Explores codebase and produces implementation plans for complex features. |
| researcher model: sonnet | Multi-source web researcher. Use for questions that need evidence from several external sources. Searches broadly, fetches primary sources, adversarially verifies claims, and returns a cited, decision |
| reviewer model: sonnet | Reviews code for bugs, style, security, performance. Use after implementing features or before committing. |
| security-auditor model: opus | Deep security audit targeting AI-generated code weaknesses. Thorough analysis with actionable fixes. |
| security-scanner model: sonnet | Scans for common security vulnerabilities. |
| skill-author model: opus | Authors and edits Claude Code skills, rules, and agent definitions for Sameer's ~/.claude setup. Knows the conventions and file formats. Use to create or refactor a skill/rule/agent correctly and cons |
Similar rigs
timurgaleev/vibestack
Sixty commands for AI coding assistants — /office-hours to shape an idea, /review before you merge, /ship to open the PR — plus the standing rules they assume. One install covers Claude Code, Cursor, Kiro and Codex CLI. Plain bash, MIT, no
Skill Collector 7.1k tok ·
Ertinox7711/SGRR-AGI-V2
⚡ The Claude Code power-rig in 1 prompt: settings.json, CLAUDE.md AGI-proactive, context hooks, memory, 12 plugins + an anti-leak pipeline of secrets to participate in the configuration without risk. 🇫🇷 FR-native.
Orchestrator 11.1k tok ·
kangraemin/claude-config
Claude Code global config - agents, commands, rules, hooks
YOLO Cowboy 11.6k tok ·
AndreAlbuquerque/claude-config
Personal Claude Code config — global CLAUDE.md, agents (@pm, @visionary, @discovery, @designer, @engineer, @implementer, @researcher, @reviewer, @qa), and skills, synced across machines.
Orchestrator 3.0k tok ·