~ / rigs / joymin5655 / Agent

joymin5655/Agent

Multi-runtime AI agent governance harness — Claude Code · Codex · Gemini under one YAML policy, with portable security hooks

↗ GitHub ★ 2 MIT updated 8d ago project Claude CodeCodex Claude plugin
stack: PythonShell
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~3.8k 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 joymin5655/Agent/agents ./rig-agent/agents
$ npx degit joymin5655/Agent/commands ./rig-agent/commands
$ npx degit joymin5655/Agent/skills ./rig-agent/skills
$ npx degit joymin5655/Agent/hooks ./rig-agent/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 joymin5655/Agent/extras/skills/brain-ingest .claude/skills/brain-ingest
$ npx degit joymin5655/Agent/extras/skills/code-tour .claude/skills/code-tour
$ npx degit joymin5655/Agent/extras/skills/harness-audit .claude/skills/harness-audit
$ npx degit joymin5655/Agent/extras/skills/harness-loop .claude/skills/harness-loop
$ npx degit joymin5655/Agent/extras/skills/loop .claude/skills/loop
$ npx degit joymin5655/Agent/extras/skills/manager-audit .claude/skills/manager-audit
$ npx degit joymin5655/Agent/extras/skills/persona-review .claude/skills/persona-review
$ npx degit joymin5655/Agent/extras/skills/reorg-sync .claude/skills/reorg-sync
$ npx degit joymin5655/Agent/extras/skills/worker-setup .claude/skills/worker-setup
$ npx degit joymin5655/Agent/extras/skills/writing-critique .claude/skills/writing-critique
$ npx degit joymin5655/Agent/skills/council-review .claude/skills/council-review
$ npx degit joymin5655/Agent/skills/harness-help .claude/skills/harness-help
$ npx degit joymin5655/Agent/skills/spec .claude/skills/spec
$ npx degit joymin5655/Agent/skills/supervise .claude/skills/supervise
$ npx degit joymin5655/Agent/skills/verify-completion .claude/skills/verify-completion
$ npx degit joymin5655/Agent/skills/wrap .claude/skills/wrap
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/joymin5655/Agent/main/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/plan-checker.md https://raw.githubusercontent.com/joymin5655/Agent/main/agents/plan-checker.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/joymin5655/Agent/main/agents/security-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 (16)

Subagents (3)

code-reviewer
model: sonnet
Reviews a diff for correctness, logic, maintainability, and style. Use at wrap/PR time when the diff is review-tier tier>=1 (core/infra/review-tier.sh), or immediately when the change touches risk-are
plan-checker
model: sonnet
Checks a written plan.md against its spec.md for decision coverage before the plan is approved. Use after /spec writes plan.md and before approval, or when the user says "check this plan" / "plan revi
security-reviewer
model: opus
Audits diffs for OWASP Top 10, secret exposure, auth/authz bugs, injection, and unsafe crypto. Use PROACTIVELY after editing auth, API endpoints, input handling, or crypto — or any path like **/auth/*

Slash commands (1)

/project-init

Similar rigs

copied ✓