agentrigs
+ submit rig
~ / rigs / GreenLv / skillferry

GreenLv/skillferry

Portable agent workspace across Codex, Claude Code, and DeepSeek Harness

↗ GitHub ★ 0 Apache-2.0 updated 1mo ago project Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~95 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 GreenLv/skillferry/skills ./rig-skillferry/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 GreenLv/skillferry/examples/starter-workspace/skills/release-checklist .claude/skills/release-checklist
$ npx degit GreenLv/skillferry/examples/starter-workspace/skills/setup-skillferry .claude/skills/setup-skillferry

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

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

Skills (2)

release-checklistsetup-skillferry

Similar rigs

zzallirog/agent-atlas
A modular working-memory layout for LLM agents that work across many repositories.
★ 1 project Codex 1 skills 5mo ago
Minimalist 904 tok ·
herbeus/graft
One shared directory of AI-agent context, linked into every repository you work on - found by git remote URL, not by hardcoded path
★ 0 setup Claude Code 1 skills 1mo ago
Minimalist 33 tok ·
seanchatmangpt/claude-code-config-lsp
LSP 3.18 server for Claude Code config files (settings.json, CLAUDE.md, hooks, agents, skills)
★ 1 setup Claude Code 1 mcp 6 skills 6 agents 1 hooks 15d ago
Orchestrator 6.4k tok ·
maximhq/bifrost
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
★ 8,548 project Claude CodeCodex 15 skills 5d ago
Skill Collector 16.5k tok ·
copied ✓