agentrigs
+ submit rig
~ / rigs / atlax-tech / harness-armor

atlax-tech/harness-armor

Self-improving, tool-first Harness Engineering Agent Skills for Claude Code, Codex, Cursor and TRAE. Build, audit, update and verify AGENTS.md-based repositories.

↗ GitHub ★ 1 NOASSERTION updated 3mo ago personal setup Codex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~908 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 atlax-tech/harness-armor/skills ./rig-harness-armor/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 atlax-tech/harness-armor/skills/harness-build .claude/skills/harness-build
$ npx degit atlax-tech/harness-armor/skills/harness-check .claude/skills/harness-check
$ npx degit atlax-tech/harness-armor/skills/harness-init .claude/skills/harness-init
$ npx degit atlax-tech/harness-armor/skills/harness-promotion .claude/skills/harness-promotion
$ npx degit atlax-tech/harness-armor/skills/harness-prompt .claude/skills/harness-prompt
$ npx degit atlax-tech/harness-armor/skills/harness-update .claude/skills/harness-update
$ npx degit atlax-tech/harness-armor/skills/harness .claude/skills/harness

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 (7)

harness-buildharness-checkharness-initharness-promotionharness-promptharness-updateharness

Similar rigs

waqas1412/claude-harness
Portable, self-adapting Claude Code harness: advisor agents, profile-driven /pr and /ticket skills, enforcement hooks, and /harness-init that tailors any repo.
★ 1 setup Claude Code 9 skills 3mo ago
Pragmatist 3.8k tok ·
Gruci/agent-harness
Harness engineering for Claude Code & Codex: hooks and gates that mechanically enforce your project rules, instead of trusting the agent to remember them.
★ 1 setup Claude CodeCodex 18 skills 6 agents 21 hooks 8d ago
YOLO Cowboy 4.6k tok ·
gastonlarap-a11y/claude-code-setup
—
★ 1 setup Claude CodeCodexGemini CLI 1 mcp 28 skills 2mo ago
Fort Knox 6.6k tok ·
stellarlinkco/myclaude
Multi-agent orchestration workflow (Claude Code Codex Gemini OpenCode)
★ 2,753 setup Claude Code 11 skills 32 agents 5mo ago
Orchestrator 3.1k tok ·
copied ✓