celaldrg/subagentlint
Lint Claude Code subagent files (.claude/agents) before they fail silently: frontmatter typos, missing descriptions, duplicate names, broken hook scripts, description token budget. Zero-dependency Python CLI.
stack: Python
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit celaldrg/subagentlint/examples/broken/.claude ./rig-subagentlint # inspect, then merge into .claude/ 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 celaldrg/subagentlint/examples/broken/.claude/skills/api-conventions .claude/skills/api-conventions $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/celaldrg/subagentlint/main/examples/broken/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/db-reader.md https://raw.githubusercontent.com/celaldrg/subagentlint/main/examples/broken/.claude/agents/db-reader.md $ curl -fsSL --create-dirs -o .claude/agents/no-desc.md https://raw.githubusercontent.com/celaldrg/subagentlint/main/examples/broken/.claude/agents/no-desc.md $ curl -fsSL --create-dirs -o .claude/agents/notes.md https://raw.githubusercontent.com/celaldrg/subagentlint/main/examples/broken/.claude/agents/notes.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/celaldrg/subagentlint/main/examples/broken/.claude/agents/review/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/skip-me.md https://raw.githubusercontent.com/celaldrg/subagentlint/main/examples/broken/.claude/agents/skip-me.md $ curl -fsSL --create-dirs -o .claude/agents/typo-reviewer.md https://raw.githubusercontent.com/celaldrg/subagentlint/main/examples/broken/.claude/agents/typo-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/window.md https://raw.githubusercontent.com/celaldrg/subagentlint/main/examples/broken/.claude/agents/window.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/celaldrg/subagentlint/main/examples/ok/.claude/agents/code-reviewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (1)
Subagents (9)
| code-reviewer model: sonnet | Expert code review specialist. Use proactively after writing or modifying code. |
| db-reader | Execute read-only database queries. Use when analyzing data or generating reports. |
| no-desc model: haiku | — |
| notes | — |
| code-reviewer | Another reviewer living in a subfolder of the same agents tree. Only one of these will load. |
| -secret | This name starts with a hyphen, so Claude Code will not load the file at all. |
| typo-reviewer | Looks at diffs. |
| window model: sonnet | Reads long log files and reports the errors it finds, then summarises recurring patterns. |
| code-reviewer model: inherit | Expert code review specialist. Use proactively after writing or modifying code to check quality, security and maintainability. |
Similar rigs
AlejoPH03/roundtrip-travel-app
Social travel app prototype: friends' trips on a 3D globe, trusted recommendations and group trip planning. Vanilla JS, no build step.
Minimalist 1.6k tok · · Q3
aihpi/workshop-rapid-prototyping
Rapid Prototyping via Vibe Coding — AISC workshop series
Minimalist 970 tok · · Q3
berni23/laight
Run teams of coding agents in tmux from YAML workflows, with one queue for every human decision.
Pragmatist 8.3k tok · · Q35
lgamorim/claude-rules
Opinionated Claude Code rules for .NET and C# with conventions, architecture guidance, and guardrails for idiomatic, production-ready code.
Pragmatist 4.2k tok · · Q3