vishalvasant/vishalvasant-first-assistant

Gemini 2.5 Pro

gemini

1048kinput·65.536koutput

Claude 3.7 Sonnet

anthropic

200kinput·8.192koutput

Claude 3.5 Haiku

anthropic

200kinput·8.192koutput

Claude 3.5 Sonnet

anthropic

200kinput·8.192koutput

Gemini 2.0 Flash

gemini

1048kinput·8.192koutput

Rules

<important_rules>
  When modifying code:
  - Automatically locate the relevant file(s) in the project using identifiers like class names, filenames, or function names.
  - Do not show a preview. Instead, **apply the changes directly** to the located file(s).
  - Modify the file with in-place edits, clearly annotating changes using `// {{ modified }}` for tracking.
  - Maintain the full context around the modified sections to ensure code clarity and consistency.
  - Use the proper file path to apply changes, such as:
    ```cpp src/gui/BandwidthWidget.cpp
    ```

  Token Usage Management:
  - Optimization:
    - Combine changes to multiple files into a **single request** where feasible.
    - Only split into separate requests if token or token limit would be exceeded.
  After change is applied:
  - Ask:  
    **"Do you want to push this change to a git branch named after the task/issue ID?"**
  - If confirmed:
    - Automatically gather required Git information from the terminal or environment:
      - Repository URL
      - Git username
      - Remote name (default to `origin` if not specified)
      - Current branch (if needed)
    - Create and push to a branch named like `feature/<task-id>` or `fix/<issue-id>`
    - Notify the user with confirmation once pushed.
</important_rules>

Docs

Langchain Docshttps://python.langchain.com/docs/introduction/

Prompts

My prompt

Sequential Thinking Activation

<!-- Sequential Thinking Workflow -->
<assistant>
    <toolbox>
        <mcp_server name="sequential-thinking"
                        role="workflow_controller"
                        execution="sequential-thinking"
                        description="Initiate the sequential-thinking MCP server">
            <tool name="STEP" value="1">
                <description>Gather context by reading the relevant file(s).</description>
                <arguments>
                    <argument name="instructions" value="Seek proper context in the codebase to understand what is required. If you are unsure, ask the user." type="string" required="true"/>
                    <argument name="should_read_entire_file" type="boolean" default="true" required="false"/>
                </arguments>
                <result type="string" description="Context gathered from the file(s). Output can be passed to subsequent steps."/>
            </tool>
            <tool name="STEP" value="2">
                <description>Generate code changes based on the gathered context (from STEP 1).</description>
                <arguments>
                    <argument name="instructions" value="Generate the proper changes/corrections based on context from STEP 1." type="string" required="true"/>
                    <argument name="code_edit" type="object" required="true" description="Output: The proposed code modifications."/>
                </arguments>
                <result type="object" description="The generated code changes (code_edit object). Output can be passed to subsequent steps."/>
            </tool>
            <tool name="STEP" value="3">
                <description>Review the generated changes (from STEP 2) and suggest improvements.</description>
                <arguments>
                    <argument name="instructions" type="string" value="Review the changes applied in STEP 2 for gaps, correctness, and adherence to guidelines. Suggest improvements or identify any additional steps needed." required="true"/>
                </arguments>
                <result type="string" description="Review feedback, suggested improvements, or confirmation of completion. Final output of the workflow."/>
            </tool>
        </mcp_server>
    </toolbox>
</assistant>

Context

@code

Reference specific functions or classes from throughout your project

@docs

Reference the contents from any documentation site

@diff

Reference all of the changes you've made to your current branch

@terminal

Reference the last command you ran in your IDE's terminal and its output

@problems

Get Problems from the current file

@folder

Uses the same retrieval mechanism as @Codebase, but only on a single folder

@codebase

Reference the most relevant snippets from your codebase

@os

Reference the architecture and platform of your current operating system

Data

No Data configured

MCP Servers