Skip to content

lawzava/megapowers / plugins/megapowers/skills/orchestrating

orchestrating

Verified

Use when two or more independent lanes can run in parallel, an output-only lane protects lead context from raw payload, or a handoff or durable run needs coordination. Covers fan out, spawn agents, split the work, delegate lanes, review while building, and independent files or services to inspect at once.

FileKindSize
SKILL.mdskill md3.3 KB
assets/agent-capabilities.mdmarkdown3.1 KB
references/fences.mdmarkdown1.5 KB
references/native-dispatch.mdmarkdown5.2 KB
references/review-contract.mdmarkdown1.3 KB

references/review-contract.md

View on GitHub
# Reviewer return and lead decision

Require this return from each reviewer, native or external:

```text
verdict: pass | fail
scope.creep: [] # unrequested changes, drive-by refactors, new dependencies
scope.shrink: [] # stubs, TODOs, weakened/skipped/deleted tests,
                 # loosened assertions, unconfirmed acceptance items
findings:
  - severity: blocker | major | nit
    file: repo-relative path
    line: line number
    claim: defect and failing input or sequence
    evidence: observation, test, or artifact that supports the claim
```

Use explicit empty lists and state verification limits. The lead computes fail
when any blocker, major, scope.creep or scope.shrink exists, regardless of the
reviewer's stated verdict. Nits never fail. Missing fields, truncated returns
and unavailable reviews are gaps, not passes. Check findings yourself; record
concrete disproof for false positives and fix real failures before approval.

Set the correction-round cap before dispatch and retain it across fresh agents.
A spent budget leaves unresolved findings open for the user. Start a fresh
agent per correction round with the original brief plus all later directives;
review only fixes, affected boundaries and new evidence. See
[correction rounds](../../independent-review/references/correction-rounds.md).
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: 472kUpdated 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: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated 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: 323kUpdated Claude CodeCodexVerifiedInstall