mistral-vibe: Skill for Claude Code

.agents/skills/vibe-async/SKILL.md

vibe-async is a skill for Claude Code, Codex from mistralai/mistral-vibe. It costs 45 tokens per session (436 once invoked), scanned A, original, Apache-2.0.

A set of rules for writing asynchronous and concurrent Python code in Mistral Vibe, an AI coding tool. It covers background work, streaming results, user-interface communication, and HTTP requests.

In plain words
What is it for?
It guides work on the agent loop, network clients, streamed output, background tasks, and Textual interfaces. Textual is a Python framework for terminal user interfaces.
Why use it?
It helps prevent slow tasks from freezing the text interface and keeps communication between the agent and interface consistent.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); $skill-name invocation.

This is mistralai/mistral-vibe's own configuration. It tells Claude Code and Codex how to work on mistral-vibe itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mistral-vibe configures →

About the project

Mistral Vibe is a command-line coding assistant that lets users converse with a codebase and use natural language to explore or change projects. Developers use it for file editing, code searching, version-control tasks, and shell commands through Mistral’s models. Its catalogue add-ons provide skills and instructions for customizing the assistant’s workflows.

mistralai/mistral-vibe · 4,933 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to mistralai/mistral-vibe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mistralai/mistral-vibe/main/.agents/skills/vibe-async/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mistralai/mistral-vibe

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 vibe-async

README.md
[![agentmods](https://agentmods.dev/badge/skills/mistralai/mistral-vibe/vibe-async/github.svg)](https://agentmods.dev/skills/mistralai/mistral-vibe/vibe-async)
Your own site
<a href="https://agentmods.dev/skills/mistralai/mistral-vibe/vibe-async"><img src="https://agentmods.dev/badge/skills/mistralai/mistral-vibe/vibe-async/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.

agentmods 80×15 button for vibe-async

Your own site · 80×15
<a href="https://agentmods.dev/skills/mistralai/mistral-vibe/vibe-async"><img src="https://agentmods.dev/badge/skills/mistralai/mistral-vibe/vibe-async.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00045 $0.00436
Opus 5 $0.00023 $0.00218
Sonnet 5 $0.00009 $0.00087
Haiku 4.5 $0.00005 $0.00044

Measured 11d ago against content hash 45f1672c6686, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vibe-async 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 11d 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.

.agents/skills/vibe-async/SKILL.md · 37 lines

What it actually says

Vibe Async Patterns

Conventions for async and concurrent code in Vibe. Apply when touching the agent loop, Textual event loop, HTTP clients, streaming, or any async code.

Runtime

  • asyncio is the orchestration runtime in the agent loop and tool execution. Use asyncio.create_task + queues for concurrent work, not blanket gather.

Blocking work

  • Never run CPU-heavy or I/O-bound code on the UI thread. The Textual TUI and the agent loop share one event loop, so anything blocking (large JSON/Pydantic serialization, os.fsync, subprocess calls, recursive globs) freezes the UI — offload it with asyncio.to_thread.
  • Async file wrappers don't make blocking syscalls non-blocking.
  • Use anyio.Path for file I/O on async paths.

Streaming

  • Streaming surfaces return AsyncGenerator[Event, None], not coroutines.

Core-to-TUI communication

  • Route core-to-TUI communication through vibe.app_server. Server requests such as approvals and user input become canonical Vibe events; neither the TUI nor app server may register callbacks, listeners, or message observers directly on the agent loop.

HTTP clients

  • When Vibe owns an HTTP client, use VibeAsyncHTTPClient from vibe.utils.http instead of httpx.AsyncClient so proxy env vars are handled consistently.
  • Its CIDR NO_PROXY matching applies only to IP-literal request hosts; do not resolve DNS before proxy selection.
  • Mock outbound HTTP with respx in tests.
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. 11d ago First seen · 37 lines · 45 tokens per session scan A 45f1672c6686

Subscribe to this mod's changes

vibe-async is a skill published in the GitHub repository mistralai/mistral-vibe (4,933 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 436 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…

K-Dense-AI/scientific-agent-skills · 98 tokens

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

rocm-kernels

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…

huggingface/kernels · 93 tokens

holoscan-install-wheel

Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.

NVIDIA/skills · 37 tokens

typing-exclusion-worker

Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.

getsentry/skills · 57 tokens