~ / rigs / Sanexxxx777 / curated-claude-code

Sanexxxx777/curated-claude-code

A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

↗ GitHub ★ 17 mit updated 1mo ago project Claude Code
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~980 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 Sanexxxx777/curated-claude-code/agents ./rig-curated-claude-code/agents
$ npx degit Sanexxxx777/curated-claude-code/skills ./rig-curated-claude-code/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 Sanexxxx777/curated-claude-code/skills/goal .claude/skills/goal
$ npx degit Sanexxxx777/curated-claude-code/skills/konsilium .claude/skills/konsilium
$ npx degit Sanexxxx777/curated-claude-code/skills/longread .claude/skills/longread
$ npx degit Sanexxxx777/curated-claude-code/skills/pre-push .claude/skills/pre-push
$ npx degit Sanexxxx777/curated-claude-code/skills/proof .claude/skills/proof
$ npx degit Sanexxxx777/curated-claude-code/skills/ship-secure .claude/skills/ship-secure
$ npx degit Sanexxxx777/curated-claude-code/skills/system-health .claude/skills/system-health
$ npx degit Sanexxxx777/curated-claude-code/skills/teach .claude/skills/teach
$ npx degit Sanexxxx777/curated-claude-code/skills/vet .claude/skills/vet
$ npx degit Sanexxxx777/curated-claude-code/skills/workflow-upgrade .claude/skills/workflow-upgrade
$ curl -fsSL --create-dirs -o .claude/agents/adversarial-verifier.md https://raw.githubusercontent.com/Sanexxxx777/curated-claude-code/main/agents/adversarial-verifier.md
$ curl -fsSL --create-dirs -o .claude/agents/tool-scout.md https://raw.githubusercontent.com/Sanexxxx777/curated-claude-code/main/agents/tool-scout.md

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 (10)

Subagents (2)

adversarial-verifierAdversarially verify a single claim or finding — actively try to REFUTE it, default to "refuted" when uncertain. Use to check bug reports, audit findings, or research claims before trusting them. Read
tool-scoutRead-only scout for the /vet pipeline — read a candidate tool's repo / README / docs and return a structured report (what it is, license, liveness, install method, security flags, dependencies). Never

Similar rigs

copied ✓