try-works/role-model / .agents/skills/recursive-mode
recursive-mode
UnverifiedRepository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance. Use when executing recursive-mode runs, resuming a run, locking a phase, or verifying locks.
scripts/run-recursive-benchmark.ps1
View on GitHubparam(
[ValidateSet("local-first-planner", "team-capacity-board", "release-readiness-dashboard")]
[string]$Scenario = "local-first-planner",
[ValidateSet("codex", "kimi", "opencode", "all")]
[string]$Runner = "all",
[string]$WorkspaceRoot = "",
[string]$CodexModel = "gpt-5.1",
[string]$KimiModel = "kimi-k2-5",
[string]$OpenCodeModel = "opencode/gpt-5-nano",
[int]$MaxMinutes = 60,
[int]$CommandTimeout = 900,
[int]$PreviewTimeout = 45,
[string]$NpmCommand = "npm",
[ValidateSet("sequential", "parallel")]
[string]$ArmMode = "sequential",
[double]$HintPenalty = 5,
[switch]$ListScenarios,
[switch]$PrepareOnly,
[switch]$SkipNpmInstall
)
Set-StrictMode -Version Latest
$ErrorActionPreference = "Stop"
$python = $null
if (Get-Command python -ErrorAction SilentlyContinue) {
$python = "python"
} elseif (Get-Command py -ErrorAction SilentlyContinue) {
$python = "py"
} else {
throw "Python is required to run run-recursive-benchmark.py."
}
$scriptPath = Join-Path $PSScriptRoot "run-recursive-benchmark.py"
$arguments = @()
if ($python -eq "py") {
$arguments += "-3"
}
$arguments += $scriptPath
$arguments += "--scenario"
$arguments += $Scenario
$arguments += "--runner"
$arguments += $Runner
$arguments += "--codex-model"
$arguments += $CodexModel
$arguments += "--kimi-model"
$arguments += $KimiModel
$arguments += "--opencode-model"
$arguments += $OpenCodeModel
$arguments += "--max-minutes"
$arguments += $MaxMinutes
$arguments += "--command-timeout"
$arguments += $CommandTimeout
$arguments += "--preview-timeout"
$arguments += $PreviewTimeout
$arguments += "--npm-command"
$arguments += $NpmCommand
$arguments += "--arm-mode"
$arguments += $ArmMode
$arguments += "--hint-penalty"
$arguments += $HintPenalty
if ($WorkspaceRoot) {
$arguments += "--workspace-root"
$arguments += $WorkspaceRoot
}
if ($ListScenarios) {
$arguments += "--list-scenarios"
}
if ($PrepareOnly) {
$arguments += "--prepare-only"
}
if ($SkipNpmInstall) {
$arguments += "--skip-npm-install"
}
& $python @arguments
exit $LASTEXITCODE
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 467k | Updated | Claude CodeCodex | Verified | Install |
| 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: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |