agentrigs
+ submit rig
~ / rigs / rulebased-io / harness

rulebased-io/harness

Harness engineering tools for AI agents — audit, init, recommend your project's agent-readiness (AGENTS.md, context engineering, eval)

↗ GitHub ★ 0 MIT updated 7mo ago personal setup Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~1.7k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/rulebased-io/harness

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 rulebased-io/harness/rulebased-harness/skills/audit .claude/skills/audit
$ npx degit rulebased-io/harness/rulebased-harness/skills/eval-log .claude/skills/eval-log
$ npx degit rulebased-io/harness/rulebased-harness/skills/init .claude/skills/init
$ npx degit rulebased-io/harness/rulebased-harness/skills/recommend .claude/skills/recommend

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 (4)

auditeval-loginitrecommend

Similar rigs

bentleypark/claude-code-mobile-spine
Claude Code plugin marketplace bundling mobile-spine — scaffolds a meta-repo coordinating 4 subagents (api/pm/android/ios) for mobile teams whose Android, iOS, and Backend live in 3 separate repos.
★ 1 project Claude Code 1 skills 3mo ago
Minimalist 84 tok ·
yongkyung-oh/agent-bootstrap
A minimal workflow bootstrap for AI coding agents — three markdown files that solve context loss between sessions. No framework, no dependencies.
★ 0 project Claude CodeCodex 1 skills 8mo ago
Minimalist 1.7k tok ·
quisbaum-prog/occam
Occam's razor for Claude Code and Codex: a 30-line rule set. Benchmarks vs base: 51-55% lower estimated task cost on Opus/Sonnet 5.5 max with more tests passed. 8.3% fewer tokens in a Sol 6.1 max pilot. Raw data, Docker setup and comparison
★ 17 project Claude Code 2 skills 10d ago
Minimalist 67 tok ·
fALECX/agentic-harness-tips
Claude Code setup tips: one tip, one picture, one snippet — plus a plugin that audits your repo against the list.
★ 5 setup Claude CodeCodex 2 skills 2d ago
Minimalist 393 tok ·
copied ✓