Saturate/agents
Skills, plugins, and config for AI coding agents (Claude Code, OpenCode, and more)
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 Saturate/agents/.claude ./rig-agents # 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 <redacted> .claude/skills/stats $ npx degit Saturate/agents/skills/api-design .claude/skills/api-design $ npx degit Saturate/agents/skills/azure-init .claude/skills/azure-init $ npx degit Saturate/agents/skills/chrome-devtools .claude/skills/chrome-devtools $ npx degit Saturate/agents/skills/code-metrics .claude/skills/code-metrics $ npx degit Saturate/agents/skills/code-review .claude/skills/code-review $ npx degit Saturate/agents/skills/code-simplification .claude/skills/code-simplification $ npx degit Saturate/agents/skills/codebase-audit .claude/skills/codebase-audit $ npx degit Saturate/agents/skills/commit .claude/skills/commit $ npx degit Saturate/agents/skills/debugging .claude/skills/debugging $ npx degit Saturate/agents/skills/documentation-adrs .claude/skills/documentation-adrs $ npx degit Saturate/agents/skills/doubt-driven-development .claude/skills/doubt-driven-development $ npx degit Saturate/agents/skills/evaluating-dependencies .claude/skills/evaluating-dependencies $ npx degit Saturate/agents/skills/frontend-ui-engineering .claude/skills/frontend-ui-engineering $ npx degit Saturate/agents/skills/hunting-bugs .claude/skills/hunting-bugs $ npx degit Saturate/agents/skills/idea-refine .claude/skills/idea-refine $ npx degit Saturate/agents/skills/incremental-implementation .claude/skills/incremental-implementation $ npx degit Saturate/agents/skills/knowledge .claude/skills/knowledge $ npx degit Saturate/agents/skills/launch-checklist .claude/skills/launch-checklist $ npx degit Saturate/agents/skills/make-pr .claude/skills/make-pr $ npx degit Saturate/agents/skills/managing-ports .claude/skills/managing-ports $ npx degit Saturate/agents/skills/no-ai-slop .claude/skills/no-ai-slop $ npx degit Saturate/agents/skills/node-package-management .claude/skills/node-package-management $ npx degit Saturate/agents/skills/norriq-writing .claude/skills/norriq-writing $ npx degit Saturate/agents/skills/nuget-package-management .claude/skills/nuget-package-management $ npx degit Saturate/agents/skills/performance-profiling .claude/skills/performance-profiling $ npx degit Saturate/agents/skills/plan .claude/skills/plan $ npx degit Saturate/agents/skills/pr-review .claude/skills/pr-review $ npx degit Saturate/agents/skills/pre-planning .claude/skills/pre-planning $ npx degit Saturate/agents/skills/push .claude/skills/push $ npx degit Saturate/agents/skills/safe-delete .claude/skills/safe-delete $ npx degit Saturate/agents/skills/security-deep-dive .claude/skills/security-deep-dive $ npx degit Saturate/agents/skills/ship .claude/skills/ship $ npx degit Saturate/agents/skills/skill-router .claude/skills/skill-router $ npx degit Saturate/agents/skills/spec .claude/skills/spec $ npx degit Saturate/agents/skills/tdd .claude/skills/tdd $ npx degit Saturate/agents/skills/validate-skill .claude/skills/validate-skill
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/Saturate/agents/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/Saturate/agents/main/.claude/agents/security-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/test-engineer.md https://raw.githubusercontent.com/Saturate/agents/main/.claude/agents/test-engineer.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 (37)
statsapi-designazure-initusing-chrome-devtoolscode-metricscode-reviewcode-simplificationcodebase-auditcommitdebuggingdocumentation-adrsdoubt-driven-developmentevaluating-dependenciesfrontend-ui-engineeringhunting-bugsidea-refineincremental-implementationknowledgelaunch-checklistmake-prmanaging-portsno-ai-slopnode-package-managementnorriq-writingnuget-package-managementperformance-profilingplanpr-reviewpre-planningpushsafe-deletesecurity-deep-diveshipskill-routerspectddvalidate-skill
Subagents (3)
| code-reviewer | Senior code reviewer that evaluates changes across five dimensions. Use for thorough code review before merge. |
| security-auditor | Security specialist that runs a vulnerability and threat-model pass on changes. Checks OWASP Top 10, secrets handling, auth/authz, and dependency CVEs. |
| test-engineer | Test engineer that analyzes test coverage for changes. Identifies gaps in happy path, edge cases, error paths, and concurrency scenarios. |
Similar rigs
addyosmani/agent-skills
Production-grade engineering skills for AI coding agents.
Skill Collector 3.7k tok ·
haco29/agentic-sdlc
An agentic SDLC plugin for Claude Code: /spec → /plan → /build → /test → /review → /code-simplify → /pr, with artifacts and gates. Built on addyosmani/agent-skills.
Skill Collector 2.5k tok ·
kapadias/nonna
Your AI agent says done. Nonna makes it prove it: she runs your test suite before a coding agent can stop, and blocks pushes to main and secrets in files. Claude Code plugin, plus git hooks for Codex, Cursor, Copilot, Gemini and more
Fort Knox 3.9k tok ·
HumanDealer/vibeproof
Vibe-code anything. Ship like a senior. A drop-in rulebook + skills that turn any AI coding agent (Codex, Claude Code, Cursor) into a disciplined senior engineer — built for domain experts who build with AI.
Pragmatist 2.0k tok ·