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

How to let an agent read a task's trajectory through MCP with Codex Trajectory

Have Codex call the trajectory tools to pull a safe structured summary of a specific task.

Who it is forA developer who wants Codex to review its own earlier task, or another task, without opening the viewer by hand.

The problemReviewing a prior task by hand takes time, and an agent cannot read the structured trajectory without a tool.

The outcomeA safe trajectory summary for the named task, returned through the MCP tools, that the agent can use to answer questions about what happened.

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. Ask Codex: Show the safe trajectory summary for this Codex task.
  5. Pass an explicit sessionId to get_codex_trajectory to read a specific task.

Prompt for your agent

Using the icesixgod/codex-trajectory repo, call get_codex_trajectory with the sessionId <sessionId> and return a safe summary of that task's steps and timing. Verify that the reply has no tool inputs, outputs, or raw metadata, since those stay hidden in the safe summary.

Caveat. Without an explicit sessionId, the read and show tools pick the most recently modified active task, which may not be the current task.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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