agentrigs
+ submit rig
~ / rigs / shawnla90 / recursive-drift

shawnla90/recursive-drift

a methodology for building AI agents that develop memory, voice, and personality over time. CLI-first. zero API keys. built for Claude Code.

↗ GitHub ★ 17 MIT updated 7mo ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.6k 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 shawnla90/recursive-drift/skills ./rig-recursive-drift/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 shawnla90/recursive-drift/skills/agent-routing .claude/skills/agent-routing
$ npx degit shawnla90/recursive-drift/skills/context-handoff .claude/skills/context-handoff
$ npx degit shawnla90/recursive-drift/skills/discuss .claude/skills/discuss

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)

agent-routingcontext-handoffdiscuss

Similar rigs

ikanago/dotfiles
Dotfiles deployed by Ansible 🚀
★ 5 setup Claude Code 7 skills today
Pragmatist 291 tok ·
LarryStanley/pi-delegate
Delegate coding work from Claude Code to a local pi agent — MCP tools with mid-run steer/abort, plus per-project discipline hooks.
★ 2 project Claude Code 1 mcp 9 skills 2mo ago
Pragmatist 2.9k tok ·
foliveira/harmonia
Thin lifecycle commands that orchestrate an agent roster bound by the Four Karpathy Rules, hooks that enforce everything a machine can check, and captured knowledge that compounds across sessions and projects.
★ 2 project Claude Code 15 skills 11d ago
Skill Collector 677 tok ·
avibebuilder/claude-prime
You've heard Claude Code can do amazing things. Skills, hooks, agents, memory systems — but who has time to figure all that out? Claude Prime sets it up for you in one command.
★ 113 project Claude Code 16 skills 4 hooks 5mo ago
Skill Collector 2.7k tok ·
copied ✓