Q-agent

A Claude Code setup that controls allowed commands and runs scripts at key points in a session. Hooks are automatic scripts triggered when events such as starting, stopping, or using a tool occur.

In plain words
What is it for?
Use it to load and save session memory, log shell commands, check GitHub repositories, and run project-specific reminders.
Why use it?
It helps preserve project memory, record command use, and remind the agent about unfinished work across sessions. It also limits which commands the agent can run.

Settings file for Claude Code

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.

agentmods
npx agentmods add settings/wolfpackofone/q-agent/settings
Clone the repo
git clone --depth 1 https://github.com/WolfpackOfOne/Q-agent

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 75% copy Near-identical to another mod in the catalogue.
Security

Grade A, and why

Q-agent 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.

Origin

This is a copy

75% identical to settings — 56 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/settings.json · 68 lines

What it actually says

{
  "permissions": {
    "allow": [
      "Bash(git status:*)",
      "Bash(git branch:*)",
      "Bash(git ls-remote:*)",
      "Bash(git check-ignore:*)",
      "Bash(gh repo:*)",
      "Bash(gh gist:*)",
      "Bash(gh auth:*)",
      "Bash(ls *)",
      "Bash(wc *)",
      "Bash(head *)",
      "Bash(cat > *)",
      "Bash(mkdir *)",
      "Bash(cd *)",
      "Bash(source *)",
      "Bash(env)",
      "WebSearch"
    ]
  },
  "hooks": {
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PROJECT_DIR}/.claude/hooks/stop-memory-nudge.sh"
          }
        ]
      }
    ],
    "SessionStart": [
      {
        "matcher": "startup|resume|clear|compact",
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PROJECT_DIR}/.claude/hooks/load_memory.py"
          }
        ]
      }
    ],
    "PostToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PROJECT_DIR}/.claude/hooks/log_tool_event.py"
          }
        ]
      }
    ],
    "SessionEnd": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "${CLAUDE_PROJECT_DIR}/.claude/hooks/extract_session_memory.py"
          }
        ]
      }
    ]
  }
}
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.

  1. yesterday First seen · 68 lines scan A 62eeb622c36f

Subscribe to this mod's changes

Q-agent is a settings file published in the GitHub repository WolfpackOfOne/Q-agent (5 stars, last pushed 1mo 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. It is 75% identical to settings, differing in 56 lines, and is treated as a copy.