careful

A session skill that adds safety checks before critical operations such as deleting files, changing databases, rewriting Git history, or removing Docker data.

In plain words
What is it for?
Use it before production infrastructure work, database migrations, sensitive-data operations, force pushes, or other tasks where a command typo could be costly.
Why use it?
It blocks several commands that could cause serious or irreversible data loss. The safeguards remain active for the current session after activation.

Skill for Claude CodeCodex

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 skills/brain-bootstrap/claude-code-brain-bootstrap/careful
Any agent
npx skills add brain-bootstrap/claude-code-brain-bootstrap --skill careful
Clone the repo
git clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrap

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 448 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00448
Opus 5 $0.00023 $0.00224
Sonnet 5 $0.00009 $0.00090
Haiku 4.5 $0.00005 $0.00045

Measured 2d ago against content hash 3812439d8a33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

careful scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

description: Activate safety guards for the session. Use /careful before critical operations — blocks rm -rf, DROP TABLE, git push --force, kubectl delete namespace, docker system prune via PreToolUse hook.
.claude/skills/careful/SKILL.md · 47 lines

What it actually says

/careful — Session Safety Guards

When this skill is active, the following commands are blocked via a PreToolUse hook:

Pattern Reason
rm -rf / Prevents filesystem destruction
DROP TABLE / DROP DATABASE Prevents data loss
git push --force / git push -f Prevents history rewriting
kubectl delete namespace Prevents cluster destruction
docker system prune Prevents image/volume loss
npm publish / pypi upload Prevents accidental publication

How It Works

The PreToolUse hook intercepts every Bash command and checks it against blocked patterns. If a match is found, the command is blocked (exit code 2) and a warning is injected.

When to Use

Activate before:

  • Working on production infrastructure
  • Running migration scripts
  • Handling sensitive data operations
  • Any task where a typo could be catastrophic

Deactivate by starting a new session (hooks are session-scoped).

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. 2d ago First seen · 47 lines · 45 tokens per session scan C 3812439d8a33

Subscribe to this mod's changes

careful is a skill published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 448 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

implement

TRIGGER when: user asks to implement, fix, build, or work on something — whether from a docs/wip plan OR a standalone task (bug fix, GitHub issue, one-off change). Examples: "work on task 1", "fix this bug", "implement feature X from the issue". Provides structured execution with profile detection, dependency…

serpro69/claude-toolbox · 79 tokens

review-spec

Use after implementing tasks or mid-feature to verify code matches design docs and ensure they are in sync. Detects spec deviations, missing implementations, doc inconsistencies, and outdated docs in design and implementation documentation.

serpro69/claude-toolbox · 44 tokens

chain-of-verification

Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning.

serpro69/claude-toolbox · 41 tokens

review-code

Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.

serpro69/claude-toolbox · 37 tokens

review-design

Review design, implementation, and task documents produced by design. Evaluates document quality, internal consistency, and technical soundness. Use after design completes and before starting implement.

serpro69/claude-toolbox · 37 tokens

design

Use in pre-implementation (idea-to-design) stages to understand spec/requirements and create a correct implementation plan before writing actual code. Turns ideas into a fully-formed PRD/design/specification and implementation-plan. Creates design docs and task lists in docs/wip/.

serpro69/claude-toolbox · 56 tokens