name: turn-usage
repo: https://github.com/tpte/hermes-turn-usage
sha: 728cea2b267af6f4bbc59707fb886d7df10a39e4
description: "Usage and cost footer appended to every reply — tokens, cache hit rate, cost and context occupancy, plus a per-tool time breakdown showing which tool actually consumed the wall clock. Waiting time (a blocking user prompt) is reported separately and excluded from the active-time denominator. Pure computation, never calls a model; any failure leaves the reply untouched. Disclosure — the usage footer is appended to the stored assistant reply, so it is replayed to the model on later turns and adds tokens to every turn."
maintainer: tpte
tier: community
category: general
docs_url: https://github.com/tpte/hermes-turn-usage#readme
platforms: []
capabilities:
  provides_tools: []
  provides_hooks:
    - transform_llm_output
  provides_middleware: []
  requires_env: []