Skip to content
Agentmart
Submit a tool

careful-mode

Use before running destructive or prod-facing CLI commands.

Skill by leo110047

IndexedMIT
Write a review

Chalk Labs

Need help deploying careful-mode?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/leo110047-careful-mode

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use before running destructive or prod-facing CLI commands. This skill enables an on-demand hook mode that blocks recursive force deletes, Git force-push and hard reset, Terraform destroy, kubectl delete, Helm uninstall, and destructive SQL through database clients until you disable it.

Use cases: backend, devops, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/careful-mode

What's inside

Skill name
careful-mode
Description
Use before running destructive or prod-facing CLI commands. This skill enables an on-demand hook mode that blocks recursive force deletes, Git force-push and hard reset, Terraform destroy, kubectl delete, Helm uninstall, and destructive SQL through database clients until you disable it.
License
MIT
Instructions
44 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • allowed-tools: must be a space-separated string

Files (2)

  • SKILL.md
  • careful-mode.js · scripts/

SKILL.md (first lines)

# Careful Mode

## When to Use

- Production infrastructure or shared environments.
- Destructive operations with expensive rollback.
- Temporary high-friction protection without making all hooks stricter.

## Script

- `node scripts/careful-mode.js enable`: activates `careful-mode` for the
  current Claude session.
- `node scripts/careful-mode.js status`: reports activation, state location,
  and armed guards.
- `node scripts/careful-mode.js disable`: deactivates the mode.

Flags: `--session <id>` targets another session; `--json` prints
machine-readable output.

## Guarded Operations

While active, the `PreToolUse` router blocks the Bash operations defined by
`CAREFUL_MODE_GUARDS` in `hooks/scripts/lib/hook-router/careful-mode-rules.js`.
That module is the authoritative list; the description names each guard's
`summary`, and the hook router coverage check fails when one is missing.

## Gotchas

- The guards are a focused blocklist, not a production policy engine.
- Disable the mode when the risky window ends.
- Mode state is session-scoped; check `status` before claiming it is armed or
  disabled.
- Without `${CLAUDE_PLUGIN_DATA}`, mode state falls back to temp storage.

## Completion Check

Before claiming the risky window was guarded, report:

- The command used to enable the mode.
- The `status` evidence before the risky operation.
- Whether any guarded command was blocked or allowed.
- The `status` evidence after disabling the mode.

From leo110047/goldband, MIT.

More from leo110047/goldband

Signals

Stars
0
Forks
0
Open issues
5
Last commit (this folder)
Oct 14, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/leo110047/goldband
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from leo110047

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get careful-mode running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying careful-mode?

CallGet help
Cite this page

careful-mode skill. Agent Mart. https://agentmart.dev/skills/leo110047-careful-mode (last updated 2026-10-24)