A session safety mode that warns before potentially destructive shell commands are run.

Use it while working in sensitive environments where commands such as force pushes, recursive deletion, database truncation, or disk formatting need extra review.

It lowers the chance of accidentally deleting data, overwriting branches, changing permissions broadly, or damaging containers and filesystems.

careful — Skill for Claude Code and Codex by pillip: A session safety mode that warns before potentially destructive…

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/pillip/claude-dev-kit/careful

Any agent

npx skills add pillip/claude-dev-kit --skill careful

Clone the repo

git clone --depth 1 https://github.com/pillip/claude-dev-kit

Made for: Claude Code, Codex.

Or install claude-dev-kit, the plugin that ships this one along with the rest of its 23 skills, 33 agents, 9 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pillip/claude-dev-kit/careful.svg)](https://agentmods.dev/skills/pillip/claude-dev-kit/careful)

Your own site

<a href="https://agentmods.dev/skills/pillip/claude-dev-kit/careful"><img src="https://agentmods.dev/badge/skills/pillip/claude-dev-kit/careful.svg" alt="Measured on agentmods" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 314 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.

Model	Per session	Once invoked
Fable 5	$0.00020	$0.00314
Opus 5	$0.00010	$0.00157
Sonnet 5	$0.00004	$0.00063
Haiku 4.5	$0.00002	$0.00031

Measured 4d ago against content hash fd5cb07ba436, 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (careful_guard.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

**Covered patterns**: rm -rf, git push --force, git reset --hard, git branch -D, DROP TABLE, DELETE without WHERE, TRUNCATE, mkfs, dd, chmod -R 777, kubectl delete, docker system prune.

skills/careful/SKILL.md · 23 lines

What it actually says

Careful mode is now active. All Bash commands are screened for destructive patterns before execution.

Detected patterns will be blocked with an explanation. You can re-invoke the command to confirm.

Covered patterns: rm -rf, git push --force, git reset --hard, git branch -D, DROP TABLE, DELETE without WHERE, TRUNCATE, mkfs, dd, chmod -R 777, kubectl delete, docker system prune.

Safe exceptions: Removing common build artifacts (node_modules, dist, .next, pycache, .cache, build, .turbo, coverage) is always allowed.

Bypass: Commands with --dry-run are always allowed.

To deactivate, end this conversation or start a new one without /careful.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

careful_guard.py 2.9 KB runs code

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.

4d ago First seen · 23 lines · 20 tokens per session scan C fd5cb07ba436

Subscribe to this mod's changes

careful is a skill published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 314 once invoked, about $0.0001 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.

Code Generation ai-agents autonomous-coding claude claude-code developer-tools

knowledge-base

Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…

wonderwhy-er/DesktopCommanderMCP · 112 tokens

statistical-power

Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers…

xintaofei/codeg · 190 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens

evaluating-code-models

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Orchestra-Research/AI-Research-SKILLs · 68 tokens