agent-core
agent-core provides guardrail hooks and workflow commands that every Claude Code plugin builds on, including safety-check (refuses destructive shell commands), db-guard (holds production database writes until unlocked), and post-commit feedback hooks. It includes 16 commands for everyday git workflows (plan, review, commit, create-pr, merge-pr) plus 2 agents (reviewer and security-guard) that run only when you explicitly invoke them.
Install
Source: https://github.com/adhibuchori/agent-config-kit/tree/HEAD/plugins/agent-core
What it's made of
16 commands · 2 agents · 8 hooks
- Commands
- 16
- Agents
- 2
- Skills
- 0
- MCP servers
- 0
- Hooks
- 8 · PostToolUse, PreToolUse, SessionStart, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
bash- Talks to
- nothing external detected
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 (adhibuchori).