agentrigs
+ submit rig
~ / rigs / GanyuanRan / Aegis

GanyuanRan/Aegis

Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

↗ GitHub ★ 1,320 mit updated 6d ago project Claude CodeCodexCopilot Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~2.9k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit GanyuanRan/Aegis/commands ./rig-aegis/commands
$ npx degit GanyuanRan/Aegis/skills ./rig-aegis/skills
$ npx degit GanyuanRan/Aegis/hooks ./rig-aegis/hooks

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 GanyuanRan/Aegis/skills/anti-entropy-governance .claude/skills/anti-entropy-governance
$ npx degit GanyuanRan/Aegis/skills/brainstorming .claude/skills/brainstorming
$ npx degit GanyuanRan/Aegis/skills/communicating-concisely .claude/skills/communicating-concisely
$ npx degit GanyuanRan/Aegis/skills/dispatching-parallel-agents .claude/skills/dispatching-parallel-agents
$ npx degit GanyuanRan/Aegis/skills/establishing-project-context .claude/skills/establishing-project-context
$ npx degit GanyuanRan/Aegis/skills/executing-plans .claude/skills/executing-plans
$ npx degit GanyuanRan/Aegis/skills/finishing-a-development-branch .claude/skills/finishing-a-development-branch
$ npx degit GanyuanRan/Aegis/skills/first-principles-review .claude/skills/first-principles-review
$ npx degit GanyuanRan/Aegis/skills/goal-framing .claude/skills/goal-framing
$ npx degit GanyuanRan/Aegis/skills/long-task-continuation .claude/skills/long-task-continuation
$ npx degit GanyuanRan/Aegis/skills/receiving-code-review .claude/skills/receiving-code-review
$ npx degit GanyuanRan/Aegis/skills/recording-architecture-decisions .claude/skills/recording-architecture-decisions
$ npx degit GanyuanRan/Aegis/skills/requesting-code-review .claude/skills/requesting-code-review
$ npx degit GanyuanRan/Aegis/skills/subagent-driven-development .claude/skills/subagent-driven-development
$ npx degit GanyuanRan/Aegis/skills/systematic-debugging .claude/skills/systematic-debugging
$ npx degit GanyuanRan/Aegis/skills/test-driven-development .claude/skills/test-driven-development
$ npx degit GanyuanRan/Aegis/skills/ui-ux-governance .claude/skills/ui-ux-governance
$ npx degit GanyuanRan/Aegis/skills/update-aegis .claude/skills/update-aegis
$ npx degit GanyuanRan/Aegis/skills/using-aegis .claude/skills/using-aegis
$ npx degit GanyuanRan/Aegis/skills/using-git-worktrees .claude/skills/using-git-worktrees
$ npx degit GanyuanRan/Aegis/skills/verification-before-completion .claude/skills/verification-before-completion
$ npx degit GanyuanRan/Aegis/skills/writing-plans .claude/skills/writing-plans
$ npx degit GanyuanRan/Aegis/skills/writing-skills .claude/skills/writing-skills

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 (23)

anti-entropy-governancebrainstormingcommunicating-conciselydispatching-parallel-agentsestablishing-project-contextexecuting-plansfinishing-a-development-branchfirst-principles-reviewgoal-framinglong-task-continuationreceiving-code-reviewrecording-architecture-decisionsrequesting-code-reviewsubagent-driven-developmentsystematic-debuggingtest-driven-developmentui-ux-governanceupdate-aegisusing-aegisusing-git-worktreesverification-before-completionwriting-planswriting-skills

Slash commands (3)

/brainstorm/execute-plan/write-plan

Similar rigs

RichardBray/dotfiles
My personal configuration files and settings
★ 62 setup Claude Code 14 skills 17d ago
Skill Collector 671 tok ·
emanuelnicenboim/dotfiles
Personal dotfiles - Claude Code skills & config
★ 0 setup Claude Code 14 skills 5mo ago
Skill Collector 671 tok ·
obra/superpowers
An agentic skills framework & software development methodology that works.
★ 294k project CodexGemini CLI 15 skills 12d ago
Skill Collector 3.0k tok ·
sodiumjoe/dotfiles
dotfiles
★ 49 setup Claude Code 16 skills 2 agents 2d ago
Skill Collector 1.1k tok ·
copied ✓