DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to find where a checked-in spec no longer matches code with Elephant Goldfish Model

Scan code against existing specs to report divergence between the written design and the live code.

Who it is forA maintainer who inherited a repo with specs under docs/designs/ and suspects the code has moved away from them.

The problemSpecs go stale after code changes, and nobody knows which parts of the written design still describe what runs.

The outcomeA drift report listing where the checked-in spec and the live code diverge, so the team can fix one side.

What you need first

  • An AI coding agent that can install the plugin, such as Claude Code or Codex, or any agent that can take the install request from the README
  • A local git checkout of the project you are designing for
  • A design doc file under docs/designs/ to review, or a concept to start from

Steps

  1. Install the plugin in Claude Code with claude plugin marketplace add google/elephant-goldfish-model && claude plugin install egm@egm
  2. Start Claude Code in the repo that holds your specs and code
  3. Run /egm:egm-drift-report
  4. Review each reported divergence and decide whether to update the spec or the code
  5. Commit the spec updates in the same pull request as the code change they describe (inferred, check the README)

Prompt for your agent

In the repo <repo-path>, run the EGM /egm-drift-report skill against the specs in docs/designs/. Output a list of each divergence with the spec file, the spec claim, and the code location. Verify that every listed claim quotes text that exists in the spec file.

Caveat. The README describes the drift scanner as an AST scanner, so it may not catch divergence that only shows up in behavior or configuration.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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