By withzombies
Ryan's riff on obra/superpowers: strong guidance for Claude Code as a software development assistant
Refresh context and task docs before stopping or resuming work
Distill an approved spec into context and rolling task docs
Audit test quality - identify tautological tests, coverage gaming, missing corner cases
Shape a feature into an approved markdown spec and task directory
Execute the current Now slice from a markdown task directory
Use this agent when a major project step has been completed and needs review against the original plan, requirements, and coding standards.
Use this agent when planning or designing features and you need the current codebase state, existing patterns, or verified file and module locations.
Use this agent when planning or designing features and you need current internet research, official documentation, version information, or external best-practice guidance.
Use this agent to audit test effectiveness with SRE-level scrutiny and find tautological tests, weak assertions, coverage gaming, and missing corner cases.
Use this agent to run tests, pre-commit hooks, or commits without polluting context with verbose output; it returns only the summary and failures.
Use to audit test quality with SRE scrutiny - identifies weak tests, missing cases, and creates task docs for improvements
Use when shaping a feature before implementation - turns rough ideas into an approved markdown spec and local task directory
Use when creating Claude Code hooks - covers hook patterns, composition, testing, progressive enhancement from simple to advanced
Use when encountering bugs or test failures - systematic debugging using debuggers, internet research, and agents to find root cause before fixing
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub withzombies/hyperpowers --plugin hyperpowersBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses power tools
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Workflow guidance for Claude Code and Codex.
Hyperpowers provides repo-local skills, hooks, commands, and specialized agents that help AI coding agents stay aligned with a real engineering workflow. The active workflow is markdown-first: shape the work, create a local task directory, then execute in small reviewed slices.
plans/active/.plan.md holds the approved spec.context.md captures discoveries and resume notes.tasks.md is the rolling backlog with Now, Next, Later, Blocked, and Done.plans/active/; they are not archived in the repo.Core workflow skills:
brainstorming shapes rough ideas into an approved specwriting-plans distills the spec into task docsexecuting-plans works the current slice and updates docsreview-implementation audits the implementation against the specverification-before-completion requires evidence before completion claimsmanaging-task-docs handles splitting, deleting finished local task dirs, and re-prioritizing task docsSupporting skills:
test-driven-developmentdebugging-with-toolsfixing-bugsrefactoring-diagnosisrefactoring-designrefactoring-safelydispatching-parallel-agentsbuilding-hooksskills-auto-activation/hyperpowers:brainstorm/hyperpowers:write-plan/hyperpowers:execute-plan/hyperpowers:update-task-docs/hyperpowers:review-implementationcode-reviewercodebase-investigatorinternet-researchertest-runnerHooks support:
See HOOKS.md for details.
For substantial work:
brainstorming.plans/active/<slug>/plan.md.writing-plans to fill context.md and tasks.md.executing-plans to work only the current Now slice.plans/active/.Claude Code plugin:
/plugin marketplace add withzombies/hyperpowers
/plugin install hyperpowers@withzombies-hyper
Codex skills:
.agents/skills/writing-skills when editing skillsbuilding-hooks when editing hook behaviorMIT
Claude Code-specific fork of Superpowers with native task management and CC-specific enhancements
Ryan's riff on obra/superpowers: strong guidance for Claude Code as a software development assistant
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems