~ / rigs / brianlovin / agent-config

brianlovin/agent-config

My coding agent config

↗ GitHub ★ 377 no license updated 7mo ago personal setup Claude CodeCodex
share on X
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
CONTEXT TAX · EVERY TURN
~1.4k 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 brianlovin/agent-config/agents ./rig-agent-config/agents
$ npx degit brianlovin/agent-config/skills ./rig-agent-config/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 brianlovin/agent-config/skills/agent-browser .claude/skills/agent-browser
$ npx degit brianlovin/agent-config/skills/bun .claude/skills/bun
$ npx degit brianlovin/agent-config/skills/chrome-webstore-release-blueprint .claude/skills/chrome-webstore-release-blueprint
$ npx degit brianlovin/agent-config/skills/deslop .claude/skills/deslop
$ npx degit brianlovin/agent-config/skills/favicon .claude/skills/favicon
$ npx degit brianlovin/agent-config/skills/find-skills .claude/skills/find-skills
$ npx degit brianlovin/agent-config/skills/fix-sentry-issues .claude/skills/fix-sentry-issues
$ npx degit brianlovin/agent-config/skills/grill-me .claude/skills/grill-me
$ npx degit brianlovin/agent-config/skills/knip .claude/skills/knip
$ npx degit brianlovin/agent-config/skills/playwriter .claude/skills/playwriter
$ npx degit brianlovin/agent-config/skills/rams .claude/skills/rams
$ npx degit brianlovin/agent-config/skills/react-doctor .claude/skills/react-doctor
$ npx degit brianlovin/agent-config/skills/reclaude .claude/skills/reclaude
$ npx degit brianlovin/agent-config/skills/sentry .claude/skills/sentry
$ npx degit brianlovin/agent-config/skills/simplify .claude/skills/simplify
$ npx degit brianlovin/agent-config/skills/skill-creator .claude/skills/skill-creator
$ npx degit brianlovin/agent-config/skills/tdd .claude/skills/tdd
$ npx degit brianlovin/agent-config/skills/workflow .claude/skills/workflow
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/brianlovin/agent-config/main/agents/security-reviewer.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 (18)

Subagents (1)

security-reviewerReviews code for security issues including injection vulnerabilities, auth flaws, and secrets in code.

Plugins (6)

swift-lsp@claude-plugins-officialcompound-engineering@compound-engineering-pluginfrontend-design@claude-plugins-officialcommit-commands@claude-plugins-officialfeature-dev@claude-plugins-officialcode-review@claude-plugins-official

Permissions

deny (0)
—
ask (0)
—
allow (2)
Bash(gh:*)
Bash(git:*)

Similar rigs

copied ✓