From skill-vibe
Delegate coding tasks to Mistral Vibe CLI (powered by Devstral 2.1) for cost-efficient execution. Use this skill whenever a task is straightforward, well-defined, and does not require Claude's full reasoning capabilities — simple refactors, boilerplate generation, test scaffolding, documentation updates, file renaming, linting fixes, dependency bumps, small bug fixes, formatting, or mechanical code changes. Also use when the user explicitly asks to use Vibe, Devstral, or Mistral for a task. Do NOT use for complex architectural decisions, multi-step debugging requiring deep reasoning, or security-sensitive code review.
How this skill is triggered — by the user, by Claude, or both
Slash command
/skill-vibe:vibeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Delegate simple, well-defined coding tasks to Mistral's Vibe CLI agent (powered by Devstral 2.1)
Delegate simple, well-defined coding tasks to Mistral's Vibe CLI agent (powered by Devstral 2.1)
to save Claude tokens for harder problems. Vibe runs non-interactively via --prompt and returns
results that Claude summarizes for the user.
vibe CLI installed and on PATH (install: curl -LsSf https://mistral.ai/vibe/install.sh | bash)~/.vibe/.env or MISTRAL_API_KEY env var)vibe --version; resolve any errors before using this skillIf vibe is not installed or not configured, inform the user and provide the installation
instructions above. Do NOT attempt to run vibe commands if the prerequisites are not met.
--prompt, auto-approving tool executionsAsk the user: "This looks like it could be delegated to Vibe (Devstral 2.1) to save tokens. Want me to handle it myself or delegate?"
vibe --prompt "<task description>" --max-turns <N> --max-price <dollars> 2>/dev/null
| Flag | Description | Default in --prompt mode |
|---|---|---|
--prompt "<task>" | Run non-interactively with this prompt | Required |
--max-turns N | Limit assistant turns | No limit |
--max-price N | Cost cap in USD | No limit |
--enabled-tools TOOL | Restrict to specific tools (can repeat) | All tools enabled |
--prompt mode automatically enables auto-approve (no user confirmation needed)2>/dev/null to avoid
bloating Claude Code's context window2>/dev/nullFor a contained, single-purpose task:
cd /path/to/project && vibe --prompt "Add JSDoc comments to all exported functions in src/utils.ts" --max-turns 10 --max-price 0.50 2>/dev/null
For tasks that only need to read code (no writes):
cd /path/to/project && vibe --prompt "List all API endpoints in this project with their HTTP methods and paths" --enabled-tools read_file --enabled-tools grep --max-turns 8 --max-price 0.30 2>/dev/null
For edits limited to specific files:
cd /path/to/project && vibe --prompt "Refactor the error handling in src/api/client.rs to use thiserror instead of manual impl. Only modify files in src/api/." --max-turns 15 --max-price 1.00 2>/dev/null
cd /path/to/project && vibe --prompt "Generate unit tests for the functions in src/auth/token.go. Use the standard testing package. Place tests in src/auth/token_test.go" --max-turns 12 --max-price 0.50 2>/dev/null
When constructing the --prompt string for Vibe, follow these guidelines:
Be specific and self-contained — Vibe does not have the conversation context that Claude has. Include all relevant details: file paths, function names, expected behavior, constraints.
Specify scope explicitly — Tell Vibe which files/directories to work in and which to avoid.
State the expected output — "Create a new file at X", "Modify function Y in file Z", "Print a summary to stdout".
Include language/framework context — "This is a Rust project using Actix-web", "This is a SvelteKit app with TypeScript".
Set boundaries — "Do not modify any files outside src/api/", "Do not add new dependencies".
After Vibe completes:
git diff or read the files)Devstral 2.1 pricing: $0.40/M input tokens, $2.00/M output tokens. For simple tasks, set conservative limits:
| Task type | Suggested --max-turns | Suggested --max-price |
|---|---|---|
| Boilerplate / scaffolding | 8-10 | $0.30 |
| Simple refactor | 10-15 | $0.50 |
| Test generation | 10-15 | $0.50 |
| Multi-file mechanical change | 15-20 | $1.00 |
| Read-only analysis | 5-8 | $0.20 |
User says: "Add error handling to the API calls in src/services/"
Claude's process:
cd /path/to/project && vibe --prompt "Add proper error handling (try/catch or Result types as appropriate) to all API call functions in the src/services/ directory. Preserve existing function signatures. Use the project's existing error handling patterns." --max-turns 15 --max-price 0.50 2>/dev/null
git diff --statnpx claudepluginhub kharonsec/vibe-plugin --plugin skill-vibeGuides AI as a disciplined coding partner for features, bugs, systems, refactoring. Human provides vision/decisions; AI executes with transparency, understanding, craftsmanship.
Delegates coding tasks (debug, implement, refactor) to OpenAI Codex CLI via codex exec, skipping the Node companion runtime for faster execution. Codex writes code; Claude verifies.
Leverages OpenAI Codex/GPT models for autonomous code implementation, reviews, and sandboxed task execution. Triggers on 'codex', 'use gpt', 'full-auto' etc.