agentrigs
+ submit rig
~ / rigs / r1ckyIn / harness-evolve

r1ckyIn/harness-evolve

Self-iteration engine for Claude Code — automatically detects usage patterns and routes optimization recommendations to hooks, skills, rules, CLAUDE.md, memory, and settings

↗ GitHub ★ 1 MIT updated 6mo ago personal setup Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~2.3k 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 r1ckyIn/harness-evolve/.claude ./rig-harness-evolve  # inspect, then merge into .claude/

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 r1ckyIn/harness-evolve/.claude/skills/evolve .claude/skills/evolve

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 (1)

evolve

Similar rigs

Cherwayway/agent-context-patch
Turn recurring Claude Code and OpenAI Codex mistakes into durable, reviewable workspace memory with safe local context patches.
★ 2 project Codex 3 skills today
Minimalist 562 tok ·
alliecatowo/claude-code-darwin
a self learning harness plugin for claude, inspired by mimo code
★ 0 project Claude Code 5 skills today
Pragmatist 428 tok ·
chengxuniucode/ForgeTeam
AI coding framework — one person, full team delivery. Pure Shell+Markdown, zero dependencies, works with Claude Code / Cursor / Codex / OpenCode. 开源 AI 编码框架，一人全栈交付。
★ 0 project Claude Code 13 skills 1 hooks 2mo ago
Skill Collector 748 tok ·
paulo-yamagishi/claude-code-setup
A /setup skill that audits your Claude Code config across 11 categories and a /bootstrap skill that scaffolds new projects interactively
★ 2 setup Claude Code 1 mcp 12 skills 2 agents 2 hooks 8mo ago
Skill Collector 19.2k tok ·
copied ✓