Safety logo

Safety

OrganizationPopular
langchain-ai
safety

Check secret handling, staged changes and push targets, destructive Git operations, Docker image hygiene, and new dependencies before consequential coding actions. Use for commits, pushes, container builds or publishes, dependency additions, and explicit safety reviews.

Overview

Publisherlangchain-ai
Repositorydeepagents
Skill namesafety
Stars
29.9K
Forks
4.2K
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by langchain-ai on GitHub. Read the source before you install it.

Installation

Install the Safety AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/langchain-ai/deepagents/tree/main/libs/talon/deepagents_talon/defaults/skills/safety
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/langchain-ai/deepagents.git /tmp/deepagents
mkdir -p .claude/skills
cp -r /tmp/deepagents/libs/talon/deepagents_talon/defaults/skills/safety .claude/skills/safety
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Safety in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Safety on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Safety is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Safety preflight

Use these checks before the relevant action, not as a session-wide prerequisite. This is guidance, not a tool permission or an automatic approval gate. Respect the repository's instructions and existing approval controls; if a check cannot be completed, explain the uncertainty and do not claim it passed.

Secrets

  • Treat credentials, private keys, tokens, and secret-bearing files as sensitive, regardless of their names. Do not display values in chat, commands, logs, diffs, or tool arguments. Use environment-variable names, secret-store references, or file paths where the tool supports them. Do not print the environment or decode secrets just to inspect them.
  • A workflow may need to consume a secret: use its intended secret-store, environment, or file interface without copying the value into source, history, or a public artifact. If a tool requires a literal value in a logged command or other exposed input, stop and seek a safer interface. Check presence or metadata without exposing contents where possible.
  • Before committing or publishing, inspect changed paths and diffs for accidental secrets. Avoid dumping suspected values while investigating; if exposed, contain the leak and recommend rotation through the appropriate owner.

Git writes and destructive operations

  • Before committing, inspect git status, staged paths (git diff --cached --name-only), and the staged diff using a local scanner or redacted review if it may contain secrets. Confirm only intended files are staged and no credentials or local secret files are included. Unstage unwanted files without discarding local changes; do not rely on .gitignore to protect already tracked files.
  • Before pushing, inspect the actual destination (git remote get-url <remote>), branch and refspec. Specify the intended remote and branch explicitly. Stop for clarification when the destination is unexpected or its ownership is unclear; do not assume a particular organization or forbid legitimate forks.
  • Before force-pushing, resetting, cleaning, deleting branches or stashes, or other work-losing operations, inspect what would be overwritten or removed and identify the exact target. Prefer reversible alternatives and --force-with-lease where appropriate. Obtain explicit confirmation before discarding another person's work or unrecoverable local changes; never treat a preview as authorization.

Docker

  • Before a build, check the build context, .dockerignore, Dockerfile and Compose configuration for secret-bearing files and values. Keep secrets out of COPY/ADD, ARG/ENV, command lines, and image layers; .dockerignore is not a substitute for checking explicit copies or external build contexts.
  • Use runtime secret injection or mounts for runtime needs and BuildKit secret mounts for build-time needs. Do not include secret values in Compose files or build arguments. Before publishing, verify the image destination and review relevant build history/configuration without printing suspected secrets. If exposure is suspected, do not publish; rebuild cleanly and rotate affected credentials.

Dependencies and supply chain

  • Prefer existing or standard-library functionality. Before adding a package, verify its source and registry identity, maintenance, licensing, known advisories, and why the existing dependencies do not suffice. Pin or bound versions according to the repository's conventions and review lockfile changes, lifecycle scripts, and unexpected transitive additions.
  • Use the project's declared package manager and available audit or registry-protection tools. A firewall such as sfw is optional: if an expected tool is unavailable, do not install it automatically or bypass a repository-mandated check. Report the missing protection and use approved alternatives or ask how to proceed when it is required. Never claim an unrun scan passed.

Frequently asked questions

What does the Safety AI skill do?

Check secret handling, staged changes and push targets, destructive Git operations, Docker image hygiene, and new dependencies before consequential coding actions. Use for commits, pushes, container builds or publishes, dependency additions, and explicit safety reviews.

Why use Safety on TypingMind?

Because you install it once and use it with any model. Safety is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Safety in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/langchain-ai/deepagents/tree/main/libs/talon/deepagents_talon/defaults/skills/safety. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Safety?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Safety?

As many as you like. As long as a model supports skills, you can use Safety with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Safety AI skill free?

Yes. It is published on GitHub by langchain-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇