AgentStack
SKILL verified MIT Self-run

Careful Mode

skill-ek33450505-claude-agent-team-careful-mode · by ek33450505

Activate careful mode — require explicit confirmation before any Write, Edit, or Bash operations. Use when working on production code or sensitive systems.

No reviews yet
0 installs
16 views
0.0% view→install

Install

$ agentstack add skill-ek33450505-claude-agent-team-careful-mode

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Careful Mode? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Careful Mode Activated

For the remainder of this session:

  1. Before EVERY Write or Edit operation, summarize the change and ask for confirmation
  2. Before EVERY Bash command, show the command and ask for confirmation
  3. Never use git push, rm, or DROP without triple-confirmation
  4. Review each file change for security implications before applying
  5. Explain your reasoning before each action — no silent changes

To deactivate, start a new session or say "deactivate careful mode".

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.