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

How to answer ten pre-code questions before writing a feature with First Pass

Have the agent answer ten questions against the real code before it writes a feature.

Who it is forA developer about to start a feature where retries, outside services, endings or shared data could break things.

The problemFeature requests that say 'be 100% sure' change how confident the answer sounds but do not make the agent check the other code that writes the same data.

The outcomeEach of the ten questions answered with a file and line, a test, or a named gap you accept.

What you need first

  • Claude Code to install the plugin (Cursor and Codex get the rules and skills, but hooks are Claude Code only)
  • A folder that holds your repos, where you start your sessions
  • Git repos with a branch to review, for the review use case (GitHub access is needed to read pull requests, inferred from the README)

Steps

  1. Complete the install and setup steps from /plugin install first-pass@first-pass and /first-pass:setup-first-pass.
  2. Run /first-pass:premortem followed by your feature request before the agent writes any code. (inferred, check the README)
  3. Read each answer. Accept a gap only when you decide to, since each gap is recorded as Not handled, because a reason.
  4. Approve the code only after the answers match the real code.

Prompt for your agent

In the <repo-name> repo, run premortem on this feature: <feature-request>. Expected output: ten answers covering running twice, stopping halfway, outside service failure, neighbors, endings, money, hostile users, words, scale and time, each as file:line, a test, or Not handled. Verify that each file:line points to code that exists.

Caveat. The questions run against code the agent can read, so answers are only as good as the repo's own files and the setup section written for it.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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