ebook-writer

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.

Security

Grade A, and why

ebook-writer 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 2d ago.

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.

.claude/settings.json · 26 lines

What it actually says

{
  "permissions": {
    "allow": [
      "Edit(/.claude/skills/code-example-validator/**)",
      "Bash(chmod +x \"/Users/kpsfamily/코딩 프로젝트/ebook-writer/.claude/skills/code-example-validator/scripts/validate_references.py\")",
      "Edit(/.claude/skills/image-generator/**)",
      "Edit(/.claude/skills/pdf-builder/**)",
      "Bash(~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project)"
    ],
    "deny": [
      "Read(.env*)",
      "Edit(.env*)",
      "Write(.env*)",
      "Bash(cat .env*)",
      "Bash(less .env*)",
      "Bash(more .env*)",
      "Bash(head .env*)",
      "Bash(tail .env*)"
    ],
    "additionalDirectories": [
      "/Users/kpsfamily/.gstack/projects",
      "/Users/kpsfamily/코딩 프로젝트/ebook-writer/.claude/skills/image-generator/references"
    ]
  }
}

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.

Related

Other settings, from other repositories