dangerous-actions

dangerous-actions is a skill for Claude Code, Codex from griddynamics/rosetta. It costs 94 tokens per session (319 once invoked), scanned A, original, Apache-2.0.

A safety procedure for coding agents handling actions that could delete data, change shared systems, or cause difficult-to-reverse damage. It requires checking the possible impact and getting explicit approval for the highest-risk actions.

In plain words
What is it for?
Assessing the impact of database changes, server actions, permission changes, CI/CD edits, branch deletion, force-pushes, and destructive scripts.
Why use it?
It makes the agent consider what could go wrong before running a risky command. This helps avoid accidental data loss, infrastructure changes, or destructive version-control operations.

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/griddynamics/rosetta/dangerous-actions
Any agent
npx skills add griddynamics/rosetta --skill dangerous-actions
Clone the repo
git clone --depth 1 https://github.com/griddynamics/rosetta

Made for: Claude Code, Codex.

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.

agentmods badge for dangerous-actions

README.md
[![agentmods](https://agentmods.dev/badge/skills/griddynamics/rosetta/dangerous-actions.svg)](https://agentmods.dev/skills/griddynamics/rosetta/dangerous-actions)
Your own site
<a href="https://agentmods.dev/skills/griddynamics/rosetta/dangerous-actions"><img src="https://agentmods.dev/badge/skills/griddynamics/rosetta/dangerous-actions.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00094 $0.00319
Opus 5 $0.00047 $0.00160
Sonnet 5 $0.00019 $0.00064
Haiku 4.5 $0.00009 $0.00032

Measured 4d ago against content hash 7512eaf48ed6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dangerous-actions scanned grade A with 0 findings 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.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

instructions/r2/core/skills/dangerous-actions/SKILL.md · 44 lines

What it actually says

<dangerous_actions>

  1. Assess BLAST RADIUS before execution.
  2. "THINK THE OPPOSITE" — what if this goes wrong?
  3. Consider safer alternatives.
  4. MUST REQUIRE EXPLICIT user approval for hard-deny tier (see below).

Examples (not limited):

  • Deleting data from actual servers
  • Using actual servers in unit testing
  • git reset, deleting branches, force-push
  • Generating destructive scripts or commands
  • Modifying shared infrastructure, CI/CD, permissions
  • Dropping or truncating database tables

Exceptions (only after blast radius):

  1. Application code itself.
  2. Just-created data you CAN fully recover.
  3. Temporary data without side-effects.
  • Assuming local action has no remote consequence.
  • Generating destructive commands in scripts without flagging.

</dangerous_actions>

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. 4d ago First seen · 44 lines · 94 tokens per session scan A 7512eaf48ed6

Subscribe to this mod's changes

dangerous-actions is a skill published in the GitHub repository griddynamics/rosetta (342 stars, last pushed today), licensed Apache-2.0. It adds 94 tokens to every session and 319 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.