Skip to content

kevogaba/finaxis-frontend / .agents/skills/using-superpowers

using-superpowers

Verified

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

references/claude-code-tools.md

View on GitHub
# Claude Code Tool Notes

Claude Code is the reference harness: skills speak its vocabulary
(`Agent` for a subagent dispatch, todos, `Skill`). These notes cover the
one place Claude Code can run a plan cheaper than the skills' default
shape. It is opt-in by your human partner and changes nothing the skills
require.

## Cheaper orchestration for subagent-driven development

The controller session is the most expensive seat in a
superpowers:subagent-driven-development run: it reads every dispatch
result and every report, and it usually runs on the session's most
capable model. Claude Code supports nested subagents (three layers below
the main conversation by default; `CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH`
adjusts it), so the whole loop can run one layer down.

When your human partner asks for it — or has said the session model is
too expensive to spend on coordination — dispatch ONE orchestrator
subagent on a mid-tier model with the plan path and the instruction to
use superpowers:subagent-driven-development end to end. The orchestrator
dispatches its own implementers and reviewers per that skill's Model
Selection; the workspace and ledger live on disk, so nothing is lost to
the extra layer. Its final message must carry the "Rulings I made" list
verbatim — that list is how the decisions reach your human partner, and
you relay it, not summarize it.

Do this only for a whole plan. Nesting a single task's dispatch buys
nothing and adds a seat.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall