agentsclimarketplace

Run1 token usage tracking

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/enterprise-information-search/run1_token-usage-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_token-usage-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

Methods for calculating or retrieving the number of tokens consumed during an LLM inference task.

SKILL.md

0.8 KB, as published. Nobody here has run it

To meet the requirement of logging consumed tokens:

  1. API Metadata: If using an external API (like OpenAI or Anthropic), retrieve usage.total_tokens from the response object.
  2. Local Calculation: If using a local model or needing a manual count, use a library like tiktoken or the model's native tokenizer.
    # Example for tiktoken
    import tiktoken
    encoding = tiktoken.get_encoding("cl100k_base")
    num_tokens = len(encoding.encode(text_input)) + len(encoding.encode(text_output))
    
  3. Validation: Always ensure the tokens value in the final JSON is a numeric type (e.g., 123) and not a string ("123").

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.