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

How to capture an agent's system prompt for each model with Orca Replay

Record the prompt a harness assembles for a given model, with the local machine details removed.

Authorization notice. Orca Replay is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forAn engineer comparing how a coding agent behaves on different models who needs the exact prompt used for each.

The problemThe prompt an agent harness builds is hidden, and it can differ between interactive and print modes and between models.

The outcomeA captured, sanitised system prompt filed under the model name, which you can compare across models.

What you need first

  • Node.js and npm, to install the orcareplay package
  • A coding agent installed locally, such as Claude Code or Codex CLI, to record a run
  • A model API key and network access for recording and for live forked turns
  • A terminal with permission to install a global npm package

Steps

  1. Run npm i -g orcareplay and clone the repo if you need the capture folder locally.
  2. Run node capture/capture.mjs claude --model claude-opus-5 to capture the prompt for that model.
  3. Read capture/README.md for the measured differences between interactive and print prompts and the sanitising rules.
  4. Repeat the capture command with another model name to get a second prompt file for comparison.

Prompt for your agent

Use the OrcaReplay repo (Continuum-AI-Corp/OrcaReplay) to capture the system prompt for the agent claude with the model <model-name> by running `node capture/capture.mjs claude --model <model-name>`. Report the file path where the sanitised prompt was saved. Verify that the saved prompt contains no local machine paths.

Caveat. The capture script is in the repo under capture/, so it needs a clone of the repo, and the README does not describe its output location beyond filing by model.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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