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.
docs/templates/hooks/session-start.ps1
View on GitHub#!/usr/bin/env pwsh
#
# Optional template - NOT auto-installed by Skills CLI.
# If your agent/runtime supports hooks, you may wire this up manually.
#
# Session Start Hook for recursive-mode
Set-StrictMode -Version Latest
$ErrorActionPreference = "Stop"
$PluginRoot = [System.IO.Path]::GetFullPath((Join-Path $PSScriptRoot "..\..\.."))
function Invoke-RecursiveBootstrap {
param(
[Parameter(Mandatory = $true)][string]$RepoRoot
)
if (Test-Path (Join-Path $RepoRoot ".recursive\RECURSIVE.md")) {
return $true
}
Write-Output "Bootstrapping recursive-mode scaffold in $RepoRoot ..."
if (Get-Command python -ErrorAction SilentlyContinue) {
& python (Join-Path $PluginRoot "scripts\install-recursive-mode.py") --repo-root $RepoRoot
if ($LASTEXITCODE -eq 0) { return $true }
}
if (Get-Command py -ErrorAction SilentlyContinue) {
& py -3 (Join-Path $PluginRoot "scripts\install-recursive-mode.py") --repo-root $RepoRoot
if ($LASTEXITCODE -eq 0) { return $true }
}
if (Get-Command pwsh -ErrorAction SilentlyContinue) {
& pwsh -NoProfile -File (Join-Path $PluginRoot "scripts\install-recursive-mode.ps1") -RepoRoot $RepoRoot
if ($LASTEXITCODE -eq 0) { return $true }
}
if (Get-Command powershell -ErrorAction SilentlyContinue) {
& powershell -ExecutionPolicy Bypass -File (Join-Path $PluginRoot "scripts\install-recursive-mode.ps1") -RepoRoot $RepoRoot
if ($LASTEXITCODE -eq 0) { return $true }
}
Write-Warning "Could not auto-bootstrap recursive-mode. Run one of the install-recursive-mode scripts manually."
return $false
}
Write-Output ""
Write-Output "recursive-mode"
Write-Output "====================="
Write-Output ""
try {
$RepoRoot = git rev-parse --show-toplevel 2>$null
if ($LASTEXITCODE -eq 0 -and $RepoRoot) {
Write-Output "Repository: $(Split-Path $RepoRoot -Leaf)"
Invoke-RecursiveBootstrap -RepoRoot $RepoRoot | Out-Null
} else {
Write-Warning "Not in a git repository. recursive-mode expects version control."
}
} catch {
Write-Warning "Not in a git repository. recursive-mode expects version control."
}
Write-Output ""
Write-Output "Available Skills:"
Write-Output " - recursive-mode - Main workflow orchestration"
Write-Output " - recursive-spec - Repo-aware requirements/spec authoring"
Write-Output " - recursive-worktree - Required worktree isolation"
Write-Output " - recursive-tdd - TDD discipline for implementation"
Write-Output " - recursive-debugging - Root-cause analysis"
Write-Output " - recursive-review-bundle - Canonical delegated review bundles"
Write-Output " - recursive-subagent - Parallel execution with fallback"
Write-Output "Optional add-ons:"
Write-Output " - recursive-benchmark - Install on demand for paired benchmark runs"
Write-Output ""
Write-Output "Quick Start:"
Write-Output " 1. Use recursive-spec to draft requirements, or identify the source plan"
Write-Output " 2. Invoke: 'Implement the run' or 'Implement requirement <run-id>'"
Write-Output " 3. recursive-mode should bootstrap missing scaffold automatically before proceeding"
Write-Output " 4. Install recursive-benchmark only when you explicitly want paired benchmark runs"
Write-Output ""
Write-Output "Documentation:"
Write-Output " - Canonical workflow: .recursive/RECURSIVE.md"
Write-Output " - Artifact templates: references/artifact-template.md"
Write-Output ""
Write-Output "====================="
Write-Output ""
$env:RECURSIVE_MODE_ROOT = $PluginRoot
$env:RECURSIVE_MODE_VERSION = "2.0.0"
Write-Output "[OK] recursive-mode ready"
Write-Output ""
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: 470k | 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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |