PlugMyPlugin
← Browse

agent-guard

JeongJaeSoon ★ 38

Agent Guard is a local-by-default security plugin that inspects user prompts, tool inputs/outputs, and changed files in Claude Code and Codex sessions to block or mask credential leaks before execution. It provides defense-in-depth protection with opt-in PII filtering and Git/CI integration, using local scanning tools like gitleaks without requiring external APIs or telemetry.

Security DevOps No API key detected runs shell

Install

> /plugin marketplace add JeongJaeSoon/agent-guard/tree/HEAD/plugins/agent-guard
> /plugin install agent-guard

Source: https://github.com/JeongJaeSoon/agent-guard/tree/HEAD/plugins/agent-guard

What it's made of

2 commands · 2 skills · 5 hooks

Commands
2
Agents
0
Skills
2
MCP servers
0
Hooks
5 · PostToolUse, PreToolUse, SessionStart, Stop, UserPromptSubmit

What it needs & plugs into

API keys
none
Paid services
none detected
External tools
"$x" *) *[!0-9.]*) *[!A-Za-z0-9._:-]*) break cksum) continue cut jq mkdir root_ok root_ok() semver semver() sh sort tail { }
Talks to
nothing external detected

Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.

Is this your plugin?

Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (JeongJaeSoon).