Agent Safety Bundle
Secure your Claude Code workflow from session loss AND security gaps.
HandoffPilot prevents lost momentum when context windows fill. It captures git state, decisions, blockers, and next steps to a structured handoff file. On resume, it verifies branch drift and asks "Continue where we left off?" Essential for long-running development sessions.
Guardrail Doctor audits your security configuration before deployment. It tests PreToolUse hooks against 15+ prompt injection bypass patterns, validates deny rules, and detects sensitive-file access attempts. Based on the real vulnerability in anthropics/claude-code#6305 where hooks claimed to block unsafe commands but silently failed.
For teams deploying Claude Code in production: HandoffPilot ensures developer productivity; Guardrail Doctor ensures security compliance.
What's included:
Both skills as separate .zip files Test payload library (15+ injection patterns) Hook configuration validator Full documentation for both skills One-time purchase, no subscription. Works with Claude Code (Guardrail Doctor) and both Claude Code + Codex (HandoffPilot).
Built for teams needing repeatable agent handoffs and pre-deployment guardrail checks before client delivery, demos, production rollouts, or compliance security review workflows.
Requirements: HandoffPilot needs git and optional Python. Guardrail Doctor needs read access to .claude/settings.json and hook files. No network calls. No external dependencies.
Works with every agent that reads SKILL.md — Claude Code, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, Windsurf, OpenClaw, and more.
One payment, lifetime access. 2 skills unlock instantly in your library.
30-day refund guarantee
Instant unlock in your library
Free updates from the creator
What's included
2 skills
Penetration-test your Claude Code agent's guardrails before you deploy. Throws prompt-injection payloads, shell-chaining, and path-traversal attempts at your PreToolUse/PostToolUse hooks and sensitive-file protections, then returns a pass/fail report on 10+ attack vectors with copy-paste remediation for every gap.
Save a coding agent's full working state to a handoff file before it hits the context limit, then resume in a fresh session without re-explaining everything. Captures the active plan, git branch, uncommitted changes, decisions, blockers, and next steps, so Claude Code or Codex picks up exactly where it stopped instead of starting cold.
See it in action
You say
Run a security audit on my Claude Code guardrails and check for path traversal and shell chaining vulnerabilities.
Your agent does
Test | Result | Evidence | Remediation Path Traversal | FAIL | cat /etc/passwd allowed | Update hook to block '/etc/' Shell Chaining | FAIL | echo 'vulnerable' && id allowed | Use command parser script Sensitive Files | PASS | .env blocked by hook | N/A
Total: 1 Pass, 2 Fail. High bypass risk detected.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.