DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to audit token spend by agent, model and session with Agent Hud Open

Review 30 days of token history and estimated API cost per agent, model, session and turn.

Who it is forA developer or team lead who wants to know which agent, model or session is using the most tokens.

The problemToken use is scattered across agent tools, so it is hard to see where the spend goes or which sessions use the most context.

The outcomeA statistics window that breaks tokens down by time, agent, model, session and turn, with cost estimates at API prices.

What you need first

  • A Mac running macOS 14 or later
  • Xcode or the Xcode Command Line Tools with a Swift 6 toolchain
  • Git, to clone the repository
  • At least one supported agent installed and signed in, such as Claude Code or Codex

Steps

  1. Run make run from the Agent Hud Open folder and let it collect local records for a while.
  2. Open the statistics window and select the last 5 hours, 24 hours, 7 days or 30 days.
  3. Review the card for each agent, then narrow the chart to the models and token kinds you care about.
  4. Open a session to see tokens per turn, how full the context window got, and each model call in a turn.
  5. Read the cost figures, noting that those marked ≈ are priced at API prices and are an estimate on a subscription, not a charge.

Prompt for your agent

In the agent-hud-open repository, run `make run`, then open the statistics window and report the token total for the last 24 hours for each agent shown. Verify that the cost figures marked ≈ are labelled as estimates.

Caveat. Cost figures are priced at the vendor's API prices where a model has one, so they are not what a subscription actually charges.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page