A project configuration plugin that formats Python code, sends notifications across operating systems, and adds a fixed guidance block to prompts for Claude and Codex.

Use it to run prompt-injection hooks at prompt submission and session restart, apply Python formatting, show notifications, point to local knowledge notes when found, and add a delegation reminder when a second-model command-line tool is available.

It keeps shared prompt guidance and formatting behavior consistent across supported sessions, while adding project-specific pointers only when the relevant context is available.

core-config — Plugin by YoungjaeDev

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add YoungjaeDev/my-claude-plugins

agentmods

npx agentmods add plugins/youngjaedev/my-claude-plugins/core-config

Clone the repo

git clone --depth 1 https://github.com/YoungjaeDev/my-claude-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

core-config scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/core-config/.claude-plugin/plugin.json · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "core-config",
  "version": "1.12.4",
  "description": "Python auto-format + cross-platform notifications + per-prompt behavioral block (`prompt_inject.sh`, shared Claude + Codex). The block is fixed; two pointers are conditional — `.llmwiki/insight/` when a knowledge root resolves in cwd, and a one-line `[council]` delegation reminder when a second-model CLI (codex / agy) is on PATH. The council line is Claude-only (Codex is itself a council member) and names the CLI roster, never a model. Work guidelines live in `~/.claude/CLAUDE.md` (English source of truth; `.ko` companion is not loaded).",
  "hooks": {
    "UserPromptSubmit": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/prompt_inject.sh\"",
            "timeout": 5000
          }
        ]
      }
    ],
    "SessionStart": [
      {
        "matcher": "compact",
        "hooks": [
          {
            "type": "command",
            "command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/prompt_inject.sh\"",
            "timeout": 5000
          }
        ]
      }
    ],
    "PostToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "command",
            "command": "if command -v python3 >/dev/null 2>&1; then python3 \"${CLAUDE_PLUGIN_ROOT}/hooks/auto-format-python.py\"; fi",
            "timeout": 10000
          }
        ]
      }
    ],
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "if command -v python3 >/dev/null 2>&1; then python3 \"${CLAUDE_PLUGIN_ROOT}/hooks/notify_osc.py\" Claude \"Task completed\"; fi",
            "timeout": 5000
          }
        ]
      }
    ],
    "Notification": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "if command -v python3 >/dev/null 2>&1; then python3 \"${CLAUDE_PLUGIN_ROOT

Read the full file on GitHub · 67 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 67 lines scan A 502a86bc9564

Subscribe to this mod's changes

core-config is a plugin published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Languages Security

core-config

Getting it into your agent

Grade A, and why

Nothing flagged

How it starts

What this file has done since we first saw it

Other plugins, from other repositories

nextjs

nextjs

claude-plugins-official

knowledge-work-plugins

ecc

ecc