agentrigs
+ submit rig
~ / rigs / Lexxes-Projects / obey

Lexxes-Projects/obey

Makes Claude actually follow your rules. Save rules with natural language, enforce them with hooks, remember them across sessions.

↗ GitHub ★ 0 mit updated 7mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~579 tokens
Featherweight · 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 Lexxes-Projects/obey/agents ./rig-obey/agents
$ npx degit Lexxes-Projects/obey/skills ./rig-obey/skills
$ npx degit Lexxes-Projects/obey/hooks ./rig-obey/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 Lexxes-Projects/obey/skills/forget .claude/skills/forget
$ npx degit Lexxes-Projects/obey/skills/remember .claude/skills/remember
$ npx degit Lexxes-Projects/obey/skills/rules .claude/skills/rules
$ curl -fsSL --create-dirs -o .claude/agents/rule-classifier.md https://raw.githubusercontent.com/Lexxes-Projects/obey/main/agents/rule-classifier.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 (3)

forgetrememberrules

Subagents (1)

rule-classifier
model: haiku
Classify a user rule into scope and enforcement mechanism. Use when analyzing a rule from /remember that has no explicit scope flag.

Similar rigs

Digital-Process-Tools/claude-remember
Persistent memory for Claude Code — identity, context, and continuity across sessions
★ 196 project Claude CodeGemini CLI 1 skills today
Minimalist 545 tok ·
code-yeongyu/codex-rules
Codex plugin that injects project rule files into model context through lifecycle hooks.
★ 14 project Codex 1 skills 1mo ago
Minimalist 428 tok ·
hereinthehive/kickstart
A Claude Code starter — fork, run /onboarding, and Claude sets itself up for your project
★ 4 project Claude Code 6 skills 2 agents 2 hooks 5mo ago
Fort Knox 896 tok ·
AltDoug/found-issues
Claude Code plugin that catches the bugs your agent shrugs at — enforced by hooks, auto-closed on merge.
★ 1 project Claude CodeCodex 2 skills 5d ago
Minimalist 2.3k tok ·
copied ✓