All notable changes to this project will be documented in this file.
Sign in to like and favorite skills
All notable changes to this project will be documented in this file.
Linear Integration: Added comprehensive Linear support for accessing issues directly from the command line with rich formatting and full context.
vibe-tools linear connectvibe-tools linear get-issue <identifier>vibe-tools linear issue <identifier>LINEAR_API_KEY.vibe-tools.envITE-123GitHub Command Improvements: Added GitHub command parameters (
--review-only--discussion-only--metadata-only--no-links--hide-resolvedmoonshotai/kimi-k2-instructqwen/qwen3-32bGROQ_API_KEYdoppler_API_KEY.env"disableDoppler": truevibe-tools.config.json--with-doc--with-docfile://askrepoplandoc--web--reasoning-effortlowmediumhighaskwebrepodocplanvibe-tools installIncreased Default Max Tokens: Raised the default maximum output tokens from 8,000 to 24,000 across all commands for more comprehensive responses.
--max-tokensUpdated Gemini Model Names to Stable Versions: Migrated all Gemini 2.5 model references from preview versions to stable versions throughout the codebase.
gemini-2.5-flash-preview-*gemini-2.5-flashgemini-2.5-pro-preview*gemini-2.5-proUpdated Default Models to latest versions:
gemini-2.5-flash-lite-preview-06-17CI=trueDEBIAN_FRONTEND=noninteractiveNONINTERACTIVE=trueCURSOR_TRACE_IDvibe-tools installSKIP_PLAYWRIGHT=1npx playwright installensurePlaywrightBrowsers()openactextractobserve--with-docvibe-tools browser open --connect-to--connect-toBrowser Mac-Chrome Lite Mode: Added
--litevibe-tools browser mac-chromeGit Diff Integration for Repo Command: Added
--with-diffvibe-tools repo--base--with-docvibe-tools browser mac-chromeclaude-3-7-sonnet-latesto3o4-minigpt-4.1gpt-4.1-minigemini-2.5-flash-preview-04-17groq-llama-3.3-70b-versatilemodelClientOptions--webclaude-3-7-sonnet-latestclaude-sonnet-4-20250514--debug--with-docaskrepoplandocDoc & Browser Commands Provider Improvements:
CTA improvement:
--with-doc <doc_url>repodoc--with-doc <doc_url>repodoccodex.md~/.codex/instructions.mdgrok-3-latestgrok-3-mini-latestXAI_API_KEY--with-doc <doc_url>repodocYoutube command: Added
youtubeGEMINI_API_KEYSupport for Reasoning Effort Parameter: Added
--reasoning-effortlowmediumhighOVERRIDE_SAFETY_CHECKS=truesrc/commands/test/command.tsqueue.add()--from-githubvibe-tools repo "explain the authentication flow" --from-github=username/repo-nameSupport for Custom Repomix Configuration: Added support for
repomix.config.jsonrepoplandocSubdirectory Analysis for Repo Command: Added
--subdirvibe-tools repo "explain the code" --subdir=src/commandsImproved Model Name Resolution: Enhanced model name handling across providers to better handle experimental and latest model versions:
-exp-*-latestgpt-4oopenai/gpt-4oSupport for OpenRouter when using MCP
By default the
mcpMCP commands require
ANTHROPIC_API_KEYOPENROUTER_API_KEYThe '--model' arg can also be used with the MCP command to set the OpenRouter model. It is ignored if the provider is Anthropic.
Google Vertex AI Authentication: Added support for Google Vertex AI authentication using JSON key files or Application Default Credentials (ADC). This update maintains backward compatibility, continuing to support the direct API key string method, while adding additional authentication options. To use this feature, set the
GEMINI_API_KEYadcgemini-2.0-flashgoogle-auth-libraryGEMINI_API_KEYGEMINI_API_KEY="./path/to/service-account.json"
Then setgcloud auth application-default login
GEMINI_API_KEYadcGEMINI_API_KEY="adc"
New Test Command: Added comprehensive test command for automated feature behavior testing:
Improved ModelBox Provider: Enhanced the ModelBox provider with improved model name handling. If a requested model is not found, vibe-tools now provides helpful suggestions for similar models. Error messages have also been clarified to better guide users on the requirement for provider prefixes when specifying ModelBox models.
Example: Improved Error Message If you use an invalid model with ModelBox, you will now receive suggestions:
Error: Model 'invalid-model' not found in ModelBox. You requested: invalid-model Similar available models: - openai/gpt-4o - anthropic/claude-3-5-sonnet Use --model with one of the above models. Note: ModelBox requires provider prefixes (e.g., 'openai/gpt-4' instead of just 'gpt-4').
Added support for MCP server overrides in the marketplace
MCP_OVERRIDESgithubUrlcommandargsvibe-tools.config.jsonmcp.overridesclaude-3-7-sonnetclaude-3-7-sonnet-thinkingp-queueglob@types/globplaywrightplaywright-core--connect-toreload-currentopenactobserveextract--console--network--no-console--no-network--connect-to.cursorrules.cursor/rules/vibe-tools.mdcUSE_LEGACY_CURSORRULESaskwebdocplanask.cursor/rules/vibe-tools.mdc.cursorrulesUSE_LEGACY_CURSORRULES=trueUSE_LEGACY_CURSORRULESgpt-4oactextractobserve--model=gpt-4ovibe-tools.config.jsonplanfileProviderthinkingProvider--fileProvider--thinkingProvider--fileModel--thinkingModel--fileMaxTokens--thinkingMaxTokens--quiet--save-to--connect-to--connect-to--connect-to--viewportopenactobserveextract--console--network--no-console--no-network--connect-to--connect-to--viewport--video--connect-toreload-current--connect-to--url=currentbrowseract <instruction> --url <url> [options]<instruction>--url <url>--delay=<milliseconds>--retry=<number>extract <instruction> --url <url> [options]<instruction>--url <url>--format=<json|csv|text>--flattenobserve <instruction> --url <url> [options]<instruction>--url <url>--interval=<milliseconds>--duration=<duration>--changes-onlyopen <url> [options]--html--console--network--screenshot=<file path>--viewport=<width>x<height>--no-headless--connect-to=<port>--timeout=<milliseconds>--viewport=<width>x<height>--headless--no-headless--connect-to=<port>--wait=<duration or selector>punycodenode:punycodepunycode/o200k_basetokenCount.encodingdoc@branch--fromGithub=username/repo@branchrefdoc--fromGithub--outputpnpm dev.cursorrulesdocInitial release with basic functionality:
--with-doc <doc_url>repodocyoutube