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

How to find where a Codex task spent its time with Codex Trajectory

Break one task's active time into tool, model/token, and unattributed shares to locate slow steps.

Credentials. The viewer reads local task logs that can contain sensitive content, so keep the safe summary view unless you need full details.

Who it is forA developer whose Codex task took much longer than expected and who wants to know whether tools or model time caused the delay.

The problemCodex task logs hold many events, and it is hard to tell which tool calls or waits consumed the time.

The outcomeA timing breakdown for the selected task showing local/tool execution, estimated model/token time, and unattributed time, with percentages, plus a timeline to locate slow calls.

What you need first

  • Codex installed on macOS, Linux, or Windows
  • uv installed (https://docs.astral.sh/uv/getting-started/installation/)
  • Local Codex task logs on the same device

Steps

  1. Run codex plugin marketplace add icesixgod/codex-trajectory
  2. Run codex plugin add codex-trajectory@icesixgod
  3. Open a new Codex task to load the plugin.
  4. In the task's right panel, select + → More tools… → Plugins and MCPs → Codex Trajectory.
  5. Find Current task timing distribution below the top statistics and click Calculate task timing.
  6. Click Recalculate after the task changes to get a new snapshot.

Prompt for your agent

Using the icesixgod/codex-trajectory repo, open the timing breakdown for the Codex task <task name or sessionId> with the show_codex_trajectory tool. Report the tool, model/token, and unattributed time shares with percentages. Verify that missing or invalid tool timing is listed separately from zero-duration events.

Caveat. Model/token time is an estimate that includes network and queueing waits, not a measure of pure token generation.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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