agentrigs
+ submit rig
~ / rigs / devduck123 / swe-os

devduck123/swe-os

Engineering judgment for people and their coding agents. One set of Markdown files: a learning site for humans, instructions for agents.

↗ GitHub ★ 0 MIT updated today project Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.2k tokens
Featherweight · median rig: 2.2k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit devduck123/swe-os/skills ./rig-swe-os/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 devduck123/swe-os/skills/build-feature .claude/skills/build-feature
$ npx degit devduck123/swe-os/skills/debug .claude/skills/debug
$ npx degit devduck123/swe-os/skills/explain .claude/skills/explain
$ npx degit devduck123/swe-os/skills/learn .claude/skills/learn
$ npx degit devduck123/swe-os/skills/review-change .claude/skills/review-change
$ npx degit devduck123/swe-os/skills/shape-project .claude/skills/shape-project
$ npx degit devduck123/swe-os/skills/start-project .claude/skills/start-project

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:

{
  "permissions": {
    "deny": [
      "Read(~/.ssh/**)",
      "Read(**/.env)",
      "Bash(rm -rf *)",
      "Read(./.env)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /*)",
      "Read(~/.aws/**)",
      "Bash(rm -rf:*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Read(**/*.key)",
      "Read(./.env.*)",
      "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(wget *)",
      "Bash(npm publish:*)",
      "Bash(gh pr merge *)",
      "Bash(chown *)",
      "Bash(docker *)"
    ]
  }
}

Skills (7)

build-featuredebugexplainlearnreview-changeshape-projectstart-project

Similar rigs

hta218/dotfiles
My personal macOS development environment — shell config, Git aliases, editor settings, and the tools I install on every new machine.
★ 31 setup Claude Code 11 skills 4 hooks 2mo ago
Skill Collector 491 tok ·
michaelbarton/dotfiles
Various configuration files
★ 12 setup Claude Code 2 skills 2d ago
Minimalist 276 tok ·
tigerless-labs/autoharness
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
★ 7,647 setup Claude Code 1 mcp 1 skills 2 agents 7d ago
Pragmatist 2.6k tok ·
nagisanzenin/engram
Evidence-based learning engine — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.
★ 1,439 project Claude Code 3 skills 1mo ago
Minimalist 185 tok ·
copied ✓