Copy this rig quick start skills (1) guardrails only
# review before running: this installs third-party code
$ npx degit MoOx/setup/.claude ./rig-setup # inspect, then merge into .claude/ copy 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 MoOx/setup/claude/skills/grill-me .claude/skills/grill-me copy Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Read(~/.ssh/id_*)",
"Read(**/.ssh/id_*)",
"Read(**/id_rsa)",
"Read(**/id_ed25519)",
"Read(**/id_ecdsa)",
"Read(**/*.pem)",
"Read(**/.env*)",
"Read(~/Library/Keychains/**)",
"Bash(security find-generic-password:*)",
"Bash(security find-internet-password:*)"
]
}
} copy json Skills (1) Permissions deny (10)
Read(~/.ssh/id_*)
Read(**/.ssh/id_*)
Read(**/id_rsa)
Read(**/id_ed25519)
Read(**/id_ecdsa)
Read(**/*.pem)
Read(**/.env*)
Read(~/Library/Keychains/**)
Bash(security find-generic-password:*)
Bash(security find-internet-password:*)
Context tax
Instructions: 337 MCP tool schemas (est.): 0 Skill metadata: 22 Subagent metadata: 0
ALWAYS-LOADED FILES (claude-code)
Estimate: characters ÷ 4 for instruction files and skill/subagent descriptions; MCP schema sizes from typical tool counts. Harnesses with deferred tool loading pay less. Method
Guardrails 2/5 · quality 20/100 ✗ No deny/ask rule for rm -rf, force-push, reset --hard, sudo…
✓ Denies reads like Read(~/.ssh/id_*)
✓ Permission prompts stay on
✗ No sandbox and no ask-first rules
Destructive-command coverage 0/22 dangerous variants covered by deny/ask rules or a blocking hook. Missed: rm -rf rm -r -f rm -fr rm -Rf find -delete git push --force git push -f git push --force-with-lease git reset --hard git clean -fdx sudo chmod -R 777 dd mkfs curl | sh terraform destroy kubectl delete npm publish DROP TABLE Known bypasses not caught: /bin/rm -rf (absolute path) bash -c 'rm -rf …' git -C . push --force
×35% 0
Secret protection breadth Not denied: .env* (Edit), *.pem / *.key (Read), *.pem / *.key (Edit), ~/.ssh (Edit), ~/.aws (Read), ~/.aws (Edit), .npmrc / .netrc (Read), .npmrc / .netrc (Edit)…
×25% 21
Hook effectiveness no PreToolUse hook
×15% 0
No-YOLO + allow-list hygiene No YOLO mode, no broad allows
×15% 100
Instruction clarity Explicit never/always rules found for: none · missing: deletion, secrets, git, prod
×10% 0
Deterministic static analysis, identical in the crawler and here. Nothing is executed. Hooks whose scripts live outside the repo are "unknown", not a pass.
Add the badge Show this rig's score in your README. Paste this Markdown:
[](https://agentrigs.dev/r/MoOx/setup/?ref=badge) copy The badge updates by itself after each daily crawl. What the score means · remove this rig
TO RAISE THIS SCORE
Add deny rules for destructive commands to .claude/settings.json, e.g. "Bash(rm -rf:*)", "Bash(git push --force:*)", "Bash(git reset --hard:*)". Add a PreToolUse hook that checks Bash commands and exits 2 to block the dangerous ones. Add "ask" rules for commands you want to confirm (e.g. "Bash(git push:*)"), or enable the sandbox with "sandbox": {"enabled": true}. Indexed from commit 09fd15ac3814 on 2026-11-17. Data is structure only — env values and anything secret-looking are stripped.