agentrigs
+ submit rig
~ / rigs / LanNguyenSi / harness

LanNguyenSi/harness

Declarative control plane for agent harnesses: one YAML for grounding, tools, memory, and hooks. Describe, validate, diff, apply.

↗ GitHub ★ 2 mit updated 1d 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
~39 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/LanNguyenSi/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 LanNguyenSi/harness/dogfood/skills/init .claude/skills/init
$ npx degit LanNguyenSi/harness/dogfood/skills/review .claude/skills/review
$ npx degit LanNguyenSi/harness/dogfood/skills/security-review .claude/skills/security-review
$ npx degit LanNguyenSi/harness/dogfood/skills/simplify .claude/skills/simplify

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)

initreviewsecurity-reviewsimplify

Similar rigs

archcore-ai/archcore
Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.
★ 63 project Claude Code 4 skills 14d ago
Minimalist 337 tok ·
lamngockhuong/termote
Self-hosted PWA to control Claude Code, Codex, GitHub Copilot or any terminal from your phone or desktop. Single Go binary streaming tmux/psmux/Herdr sessions to xterm.js, native or in a container.
★ 57 project Claude Code 1 skills 7d ago
Pragmatist 20.9k tok ·
crewship-ai/crewship
Self-hosted runtime for AI coding agents. Real Linux containers, your hardware, your keys, your data.
★ 3 project Codex 1 skills today
Pragmatist 3.1k tok ·
gilles-g/localpr
Claude Code plugin: review a local git diff in a pull-request-style page, comment on lines, and let Claude apply the review. Python stdlib only, offline.
★ 2 project Claude Code 1 skills 10d ago
Pragmatist 5.4k tok ·
copied ✓