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

How to find out why an agent session went wrong with Superpowers

Have the agent review a session transcript for skill failures and optionally package a bug report.

Credentials. The bundle is built from the session transcript, so check it for secrets or private code before you post it publicly.

Who it is forA developer whose agent skipped a skill, repeated work, ignored its plan, or used more tokens than expected, and who wants to know why.

The problemWhen a session misbehaves, it is hard to tell which skill failed and what the agent actually did.

The outcomeA report of what happened in the session, with line-level evidence, and optionally a scrubbed bundle for a bug report.

What you need first

  • A supported coding agent, such as Claude Code, Codex CLI, Cursor, or Gemini CLI, with Superpowers installed for that agent
  • A git project to work in
  • A feature or change you can describe in a few sentences

Steps

  1. Install Superpowers in your agent, for example with /plugin install superpowers@claude-plugins-official in Claude Code.
  2. Ask the agent to "figure out what went wrong with Superpowers in this session" to invoke diagnosing-superpowers.
  3. To examine an earlier session, name it in the request.
  4. Read the report and its line-level evidence.
  5. If you want to file a bug, ask for the scrubbed bundle and check it before you share it.

Prompt for your agent

Using the diagnosing-superpowers skill from the obra/superpowers repo, review the session <session name or 'this session'> and report what went wrong with superpowers. Expected output: a report with line-level evidence and an offer to package a scrubbed bundle. Verify that each finding cites a specific point in the transcript.

Caveat. The README says the skill can package a scrubbed bundle, but it does not describe what the scrubbing removes, so review the bundle yourself before you share 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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