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.
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.
npx skills add mistralai/mistral-vibe --skill write-vibe-testsgit clone --depth 1 https://github.com/mistralai/mistral-vibeWrote 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.
[](https://agentmods.dev/skills/mistralai/mistral-vibe/write-vibe-tests)<a href="https://agentmods.dev/skills/mistralai/mistral-vibe/write-vibe-tests"><img src="https://agentmods.dev/badge/skills/mistralai/mistral-vibe/write-vibe-tests/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.
<a href="https://agentmods.dev/skills/mistralai/mistral-vibe/write-vibe-tests"><img src="https://agentmods.dev/badge/skills/mistralai/mistral-vibe/write-vibe-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.01146 |
| Opus 5.5 | $0.00032 | $0.00458 |
| Sonnet 5.5 | $0.00016 | $0.00229 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
write-vibe-tests 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Vibe Tests
Use this skill to make Vibe architecture testable, not just well-shaped. Tests should protect observable behavior while allowing internals to move.
Core Principle
Test behavior through stable boundaries. Do not couple tests to private methods, internal call choreography, or temporary structure.
If a refactor changes no observable behavior but breaks many tests, the tests are probably coupled to implementation details.
Vibe Test Boundaries
| Code area | Preferred test boundary |
|---|---|
| Core use cases and services | Public function/class API, typed events, model outputs, persisted state |
| Tools | Owning app-server capability contract, typed invocation/results, permissions and user-facing errors; BaseTool.invoke/run for retained BaseTool implementations |
| LLM/backend orchestration | Native Unified Runtime through serialized app-server RPCs, with deterministic fake completion/discovery services |
| Config | Pydantic model validation, layer merge outputs, migration results |
| Sessions | Runtime session operations, durability/recovery and app-server projections; JSONL/metadata only for the supported read-only historical importer |
Terminal UI (vibe/cli-rust) |
Rust unit tests for pure logic, client-e2e scenarios and goldens for rendering and interaction (see vibe/cli-rust/AGENTS.md) |
Onboarding wizard (vibe-acp --setup) |
Textual snapshots, rendered user-visible state |
| ACP | ACP session updates and protocol-facing content, not core internals |
Prefer Fakes Over Mocks
Prefer in-memory implementations and fake adapters that implement real contracts.
- Put reusable test doubles in
tests/stubs/and name themFake*. - Make fakes small and behavior-oriented.
- Mock only at hard process, network, time, or third-party boundaries when a fake would be more complex than the behavior under test.
- Avoid assertions like "method X was called with Y" unless the call itself is the observable contract.
Legacy Or Refactor Workflow
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.
- 6d ago Changed · +1 lines 8a0453dd43c4
- 16d ago Changed · +1 lines e67dce1943ab
- 1mo ago First seen · 91 lines · 80 tokens per session scan A f6f79232a1ba
write-vibe-tests is a skill published in the GitHub repository mistralai/mistral-vibe (5,199 stars, last pushed 3d ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,146 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
composing-matchers
Build compound Gomega assertions by combining matchers — And/SatisfyAll (all pass), Or/SatisfyAny (any pass), Not (negate), WithTransform to map the actual before matching, Satisfy for an ad-hoc predicate, HaveValue to dereference pointers/interfaces, HaveField for struct fields and method results, HaveEach for every…
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
spec-driven-tests
Rebuild a package's unit test suite around a behavior specification (SPEC.md) derived from the implementation, with every test citing a numbered rule ID. Use when asked to do a spec-driven test rebuild, write a SPEC.md for a package, repeat the state or store spec process (PRs.
JavaScript Testing Patterns
Modern JavaScript testing strategies with Jest, Mocha, and testing best practices covering unit testing, integration testing, mocking, async patterns, and DOM testing.
JUnit 5 Testing
Production-grade Java unit and integration testing with JUnit 5 covering assertions, parameterized tests, lifecycle hooks, Mockito mocking, nested tests, and extensions.
maestro-work
The contract every playbook shares - the brief a writer receives, the rules it writes by, the handback it returns, and the store record the holder keeps. Reuse existing checks and add tests only for concrete uncovered behavior or risk.