agentsclimarketplace

Run1 llm token tracking

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/enterprise-information-search/run1_llm-token-tracking

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Install
npx -y skills add cxcscmu/SkillLearnBench --skill run1_llm-token-tracking

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Extracts and tracks the consumed token usage from an LLM API response to monitor API cost and utilization.

SKILL.md

1.0 KB, as published. Nobody here has run it

When querying a Large Language Model (LLM) such as OpenAI, you often need to log the consumed tokens for the request and response. Standard LLM APIs return a usage object in their response payload containing this information.

# Example of making a request and tracking token usage (OpenAI API structure)
def get_answer_and_tokens(client, prompt, context):
    response = client.chat.completions.create(
        model="gpt-4",
        messages=[
            {"role": "system", "content": f"Context: {context}"},
            {"role": "user", "content": prompt}
        ]
    )
    
    # Extract the text answer
    answer_text = response.choices[0].message.content
    
    # Extract total consumed tokens as a positive integer
    consumed_tokens = response.usage.total_tokens
    
    return answer_text, consumed_tokens

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.