A safety-mode switch for coding-agent sessions that blocks destructive commands such as deleting files, force-pushing Git changes, or dropping database tables.

Enabling or disabling protection against destructive terminal operations.

It reduces the chance that an accidental command will remove data or overwrite important work.

careful — Skill for Claude Code by bdfinst/agentic-dev-team

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.

Any agent

npx skills add bdfinst/agentic-dev-team --skill careful

Clone the repo

git clone --depth 1 https://github.com/bdfinst/agentic-dev-team

Made for: Claude Code.

Or install dev-team, the plugin that ships this one along with the rest of its 98 skills, 54 agents, 4 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/bdfinst/agentic-dev-team/careful/github.svg)](https://agentmods.dev/skills/bdfinst/agentic-dev-team/careful)

Your own site

<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/careful"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/careful/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/careful"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/careful.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 515 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00034	$0.00515
Opus 5.5	$0.00014	$0.00206
Sonnet 5.5	$0.00007	$0.00103
Haiku 4.5	$0.00003	$0.00052

Measured 1mo ago against content hash 299ed8aa5627, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

Toggle careful mode. When active, destructive commands (rm -rf, force-push,

plugins/dev-team/skills/careful/SKILL.md · 73 lines

What it actually says

Careful

Role: worker. This command toggles destructive command blocking.

You have been invoked with the /careful command.

Worker constraints

Toggle state only; do not modify code or other config.
Do not block legitimate commands beyond the destructive set.
Be concise. Confirm the new mode in one line, no preamble.

Parse Arguments

Arguments: $ARGUMENTS

off: Disable careful mode
No arguments: Enable careful mode

Steps

Enable (no arguments or any argument except "off")

Write the following JSON to .claude/hooks/careful-state.json (relative to the current repo root — not hooks/careful-state.json, which would sit inside the plugin's own shared install/cache directory and scope-lock every other concurrently-running session, worktree, and project on the machine; see issue #1900):

{
  "active": true,
  "enabled_at": "<ISO timestamp>"
}

Display:

Careful mode ON. Destructive commands will be blocked until /careful off.

Disable (`off`)

Remove .claude/hooks/careful-state.json:

rm -f .claude/hooks/careful-state.json

Display:

Careful mode OFF. Destructive commands will show warnings but not be blocked.

Notes

The hooks/destructive_guard.py hook resolves this same path per invoking repo via hooks/lib/artifact_paths.py's resolve_file("hooks", "careful-state.json") — the same .claude/-scoped convention freeze-state.json and .review-passed already use. When active, matched commands exit with code 2 (block) instead of 0 (warn).
Careful mode persists across tool calls within a session, and is scoped to the repo it was activated in.
See hooks/destructive-commands.json for the full list of detected patterns and the safe allowlist.

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.

1mo ago First seen · 73 lines · 34 tokens per session scan C 299ed8aa5627

Subscribe to this mod's changes

careful is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 515 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.

Security

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.