CookiesForAI

diagnosing-superpowers

Diagnosing Superpowers

Diagnosing Superpowers is an agent skill from Superpowers that reads a session's transcripts when work went wrong and reports what happened, with every finding tied to a file and line.

Agent skill by Jesse Vincent · Updated

Install Diagnosing Superpowers

In Claude Code, install the whole Superpowers plugin from Anthropic's official marketplace

Terminal
/plugin install superpowers@claude-plugins-official

Or install only this skill with the skills CLI

Terminal
npx skills add obra/superpowers --skill diagnosing-superpowers

Or paste this into your coding agent: Install the agent skill diagnosing-superpowers from github.com/obra/superpowers. A skill can include scripts that run on your computer, so read its source first.

What Diagnosing Superpowers does

Diagnosing Superpowers is one of the skills in Superpowers, Jesse Vincent's open-source method for AI coding agents. It loads when a Superpowers session went wrong and you want to know why: repeated work, an ignored plan, a skill that never fired, a session that took too long or cost too much. It works on the current session or a past one named by id or path, and it can prepare a bug report for the Superpowers maintainers.

In Diagnosing Superpowers, the agent first asks you one question at a time until it can state the problem, then finds the session files on disk and fills a case file under ~/.superpowers/diagnosing-superpowers/. It dispatches seven analyst subagents in parallel, one per dimension: skill timeline, plan adherence, repeated work, stumbles, quality evidence, request conflicts, and cost and time. A finding without a file path and line is dropped, and session files are never modified.

The Diagnosing Superpowers result is a report filled from a bundled template. The skill reports and does not diagnose: it states whether Superpowers was involved, but never names a defect in a skill or proposes a change. When Superpowers may be involved, or when you ask, it searches GitHub issues and drafts a new one, created only after you approve the exact text. On request it builds a bundle of the session with emails, names, secrets and private paths replaced, and reminds you that scrubbing can miss things.

When to use Diagnosing Superpowers

  • You want to know why an agent session took so long or cost so much.
  • Your agent ignored the plan, repeated work, or never used a skill you expected.
  • You want to check what a session that is still running is actually doing.
  • You want to file a bug report with the Superpowers maintainers, backed by evidence from the transcript.

When to pick something else

  • You want to debug your own code rather than an agent session: use Systematic Debugging.

Which agents Diagnosing Superpowers works in

Jesse Vincent documents Diagnosing Superpowers for Claude Code, Codex (app and CLI), Cursor, Gemini CLI, GitHub Copilot CLI, OpenCode, Antigravity, Devin CLI, Factory Droid, Grok Build CLI, Kimi Code, Pi, Qwen Code, Hermes Agent, Muse. The open skills CLI also installs it into 78 agents, including Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode (we listed it with the CLI on October 1, 2026). See where each agent looks for skills.

Superpowers is written in Claude Code's vocabulary (subagent dispatch, todos, the Skill tool) and ships tool mappings for Codex, Gemini CLI, Pi, Antigravity, Hermes Agent and Muse. Installed as the full plugin, a session-start hook loads Using Superpowers so the agent reaches for skills on its own; one skill installed with the skills CLI gets no hook and may point to sibling skills you do not have. This skill needs a subagent tool: Claude Code's Agent tool, or in Codex the multi-agent feature switched on in config.toml (multi_agent = true).

Diagnosing Superpowers license

Diagnosing Superpowers is published under MIT.

  • Grill me: grill-me is Matt Pocock's agent skill that turns your agent into a relentless interviewer, asking numbered rounds of questions about a plan or design until every decision is settled. (273,901 repository stars on October 2, 2026)
  • Brainstorming: Brainstorming is an agent skill from Superpowers that makes your coding agent work out what you want and agree a design with you before it writes any code. (293,976 repository stars on October 2, 2026)
  • Dispatching Parallel Agents: Dispatching Parallel Agents is an agent skill from Superpowers: when several problems are independent, your agent sends a focused subagent to each at once, then checks the results together. (293,976 repository stars on October 2, 2026)
  • Executing Plans: Executing Plans is an agent skill from Superpowers in which your agent works through a written plan itself, task by task with tests, then gets one fresh review of the whole branch. (293,976 repository stars on October 2, 2026)

More from Jesse Vincent

  • Finishing a Development Branch: Finishing a Development Branch is an agent skill from Superpowers: when work is done, your agent runs the tests, offers to merge, open a pull request or keep the branch, then cleans up. (293,976 repository stars on October 2, 2026)
  • Receiving Code Review: Receiving Code Review is an agent skill from Superpowers: your agent checks review feedback against the code before acting, pushes back with reasons when it is wrong, and skips the flattery. (293,976 repository stars on October 2, 2026)
  • Requesting Code Review: Requesting Code Review is an agent skill from Superpowers: your agent sends its changes to a separate reviewer subagent that checks them against the plan and grades each issue by severity. (293,976 repository stars on October 2, 2026)
  • Subagent-Driven Development: Subagent-Driven Development is an agent skill from Superpowers: your agent carries out a plan by giving each task to a fresh subagent, reviewing every task, then reviewing the whole branch. (293,976 repository stars on October 2, 2026)

Lists that include diagnosing-superpowers