~ / rigs / nguyenxp3n / agent-coding

nguyenxp3n/agent-coding

Universal engineering behavioral rules, standardized skills, and reviewer personas for AI coding agents

↗ GitHub ★ 0 no license updated 15d ago collection Claude CodeCodex
stack: JavaScript
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~4.5k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 3/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit nguyenxp3n/agent-coding/agents ./rig-agent-coding/agents
$ npx degit nguyenxp3n/agent-coding/skills ./rig-agent-coding/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 nguyenxp3n/agent-coding/skills/brainstorm .claude/skills/brainstorm
$ npx degit nguyenxp3n/agent-coding/skills/brainstorming .claude/skills/brainstorming
$ npx degit nguyenxp3n/agent-coding/skills/codebase-onboarding .claude/skills/codebase-onboarding
$ npx degit nguyenxp3n/agent-coding/skills/context-budget .claude/skills/context-budget
$ npx degit nguyenxp3n/agent-coding/skills/diagnosing-superpowers .claude/skills/diagnosing-superpowers
$ npx degit nguyenxp3n/agent-coding/skills/dispatching-parallel-agents .claude/skills/dispatching-parallel-agents
$ npx degit nguyenxp3n/agent-coding/skills/docs-drift .claude/skills/docs-drift
$ npx degit nguyenxp3n/agent-coding/skills/executing-plans .claude/skills/executing-plans
$ npx degit nguyenxp3n/agent-coding/skills/explain .claude/skills/explain
$ npx degit nguyenxp3n/agent-coding/skills/finishing-a-development-branch .claude/skills/finishing-a-development-branch
$ npx degit nguyenxp3n/agent-coding/skills/frontend-design-bar .claude/skills/frontend-design-bar
$ npx degit nguyenxp3n/agent-coding/skills/hand-off .claude/skills/hand-off
$ npx degit nguyenxp3n/agent-coding/skills/interview-me .claude/skills/interview-me
$ npx degit nguyenxp3n/agent-coding/skills/log-wiki .claude/skills/log-wiki
$ npx degit nguyenxp3n/agent-coding/skills/planning .claude/skills/planning
$ npx degit nguyenxp3n/agent-coding/skills/prototype .claude/skills/prototype
$ npx degit nguyenxp3n/agent-coding/skills/receiving-code-review .claude/skills/receiving-code-review
$ npx degit nguyenxp3n/agent-coding/skills/requesting-code-review .claude/skills/requesting-code-review
$ npx degit nguyenxp3n/agent-coding/skills/review-change .claude/skills/review-change
$ npx degit nguyenxp3n/agent-coding/skills/review-experience .claude/skills/review-experience
$ npx degit nguyenxp3n/agent-coding/skills/review-health .claude/skills/review-health
$ npx degit nguyenxp3n/agent-coding/skills/review-release .claude/skills/review-release
$ npx degit nguyenxp3n/agent-coding/skills/review .claude/skills/review
$ npx degit nguyenxp3n/agent-coding/skills/security-review .claude/skills/security-review
$ npx degit nguyenxp3n/agent-coding/skills/subagent-driven-development .claude/skills/subagent-driven-development
$ npx degit nguyenxp3n/agent-coding/skills/systematic-debugging .claude/skills/systematic-debugging
$ npx degit nguyenxp3n/agent-coding/skills/test-driven-development .claude/skills/test-driven-development
$ npx degit nguyenxp3n/agent-coding/skills/using-git-worktrees .claude/skills/using-git-worktrees
$ npx degit nguyenxp3n/agent-coding/skills/using-superpowers .claude/skills/using-superpowers
$ npx degit nguyenxp3n/agent-coding/skills/verification-before-completion .claude/skills/verification-before-completion
$ npx degit nguyenxp3n/agent-coding/skills/writing-plans .claude/skills/writing-plans
$ npx degit nguyenxp3n/agent-coding/skills/writing-skills .claude/skills/writing-skills
$ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/analyst.md
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/architect.md
$ curl -fsSL --create-dirs -o .claude/agents/database-reviewer.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/database-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/doc-updater.md
$ curl -fsSL --create-dirs -o .claude/agents/performance-optimizer.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/performance-optimizer.md
$ curl -fsSL --create-dirs -o .claude/agents/plan-reviewer.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/plan-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/react-reviewer.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/react-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/refactor-cleaner.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/security-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/silent-failure-hunter.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/silent-failure-hunter.md
$ curl -fsSL --create-dirs -o .claude/agents/typescript-reviewer.md https://raw.githubusercontent.com/nguyenxp3n/agent-coding/main/agents/typescript-reviewer.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 (32)

Subagents (12)

analyst
model: inherit
Research and analysis assistant specializing in discovery, market research, competitive analysis, brainstorming facilitation, and strategic synthesis. Creates draft research documents for human review
architect
model: inherit
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions
database-reviewer
model: inherit
PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database p
doc-updater
model: inherit
Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs and guides.
performance-optimizer
model: inherit
Performance analysis and optimization specialist. Use PROACTIVELY for identifying bottlenecks, optimizing slow code, reducing bundle sizes, and improving runtime performance. Profiling, memory leaks,
plan-reviewer
model: inherit
Implementation plan reviewer. Verifies plan is executable against current codebase — checks references, step structure, dependency ordering. Read-only. Use for Gate 2 review.
planner
model: inherit
Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for p
react-reviewer
model: inherit
Expert React/JSX code reviewer specializing in hook correctness, render performance, server/client component boundaries, accessibility, and React-specific security. Use for any change touching .tsx/.j
refactor-cleaner
model: inherit
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely r
security-reviewer
model: inherit
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injectio
silent-failure-hunter
model: inherit
Review code for silent failures, swallowed errors, bad fallbacks, and missing error propagation.
typescript-reviewer
model: inherit
Expert TypeScript/JavaScript code reviewer specializing in type safety, async correctness, Node/web security, and idiomatic patterns. Use for all TypeScript and JavaScript code changes. MUST BE USED f

Similar rigs

copied ✓