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/recursive-training-loader.ps1
View on GitHub#Requires -Version 5.1
<#
.SYNOPSIS
Progressive memory loader for recursive-mode experiential knowledge.
.DESCRIPTION
Reads the memory router plus the repository memory plane, scores memory docs
by relevance to the current task, reads the most relevant docs, scores
individual items, and returns formatted context for the agent.
This is the canonical way to load repo-specific experiential knowledge.
Any harness can call it — no MCP required.
.PARAMETER RepoRoot
Path to the git repository root.
.PARAMETER Query
Description of the current task (e.g., "implementing frontend feature").
.PARAMETER Files
Comma-separated list of file paths being modified.
.PARAMETER Subsystem
Target subsystem (e.g., "web", "artifacts", "api-worker").
.PARAMETER TaskType
Target task type (e.g., "commit-workflow", "test-validation").
.PARAMETER MaxDocs
Maximum memory docs to load (default: 3).
.PARAMETER MaxItems
Maximum items to return (default: 10).
.PARAMETER DryRun
Show what would be loaded without returning content.
.PARAMETER All
Load all items as flat list.
.EXAMPLE
.\recursive-training-loader.ps1 -RepoRoot . -Query "frontend feature" -Files "apps/web/src/App.tsx"
.EXAMPLE
.\recursive-training-loader.ps1 -RepoRoot . -Subsystem "web" -MaxDocs 5
.EXAMPLE
.\recursive-training-loader.ps1 -RepoRoot . -TaskType "commit-workflow" -MaxItems 20
#>
param(
[Parameter(Mandatory)]
[string]$RepoRoot,
[string]$Query = "",
[string]$Files = "",
[string]$Subsystem = "",
[string]$TaskType = "",
[int]$MaxDocs = 3,
[int]$MaxItems = 10,
[switch]$DryRun,
[switch]$All
)
$scriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
$pyScript = Join-Path $scriptDir "recursive-training-loader.py"
$argsList = @("--repo-root", $RepoRoot)
if ($Query) { $argsList += @("--query", $Query) }
if ($Files) { $argsList += @("--files", $Files) }
if ($Subsystem) { $argsList += @("--subsystem", $Subsystem) }
if ($TaskType) { $argsList += @("--task-type", $TaskType) }
if ($MaxDocs -ne 3) { $argsList += @("--max-docs", $MaxDocs) }
if ($MaxItems -ne 10) { $argsList += @("--max-items", $MaxItems) }
if ($DryRun) { $argsList += "--dry-run" }
if ($All) { $argsList += "--all" }
& python $pyScript @argsList
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: 466k | Updated | Claude CodeCodex | Verified | 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: 466k | 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 |