alelaguard/agentguards-plugins
Guardrails for AI coding agents: stop prompt injection, secret leaks and destructive commands in Claude Code, Codex, Gemini CLI, Copilot CLI and OpenCode. One-command install.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~2.8k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code
$ claude mcp add --transport http agentguards https://prod.agentguards.co/directory/mcp 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.
$ claude mcp add --transport http agentguards https://prod.agentguards.co/directory/mcp $ npx degit alelaguard/agentguards-plugins/claude-directory/skills/agentguards .claude/skills/agentguards $ npx degit alelaguard/agentguards-plugins/claude-selfhosted/skills/guardrails .claude/skills/guardrails $ npx degit alelaguard/agentguards-plugins/claude-selfhosted/skills/setup .claude/skills/setup $ npx degit alelaguard/agentguards-plugins/claude-selfhosted/skills/status .claude/skills/status
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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| prod.agentguards.co · "agentguards" | remote · remote | 2.5k |
Skills (4)
Similar rigs
hashgraph-online/hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Minimalist 397 tok · · Q0
MohammadMD1383/claude-plugins
Claude Code plugin marketplace: focused, open-source plugins for Claude Code
Minimalist 583 tok · · Q0
DerAlo/ari-auto-pacing
quota-pacer: Claude Code plugin that paces your work so the 5-hour and weekly quota last until the reset
Minimalist 173 tok · · Q0
Paxton-Meny/pr-review-workflow
Claude Code plugin that reviews a pull request, posts findings, edits the code to address them, and re-reviews until approval.
Minimalist 281 tok · · Q0