Regenerate provider startup context using the legacy inline compatibility branch
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add jmagly/aiwg --skill aiwg-regenerate-legacy --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Aiwg Regenerate Legacy?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/jmagly-aiwg-regenerate-legacy-aiwg)More formats (shields.io, HTML) on the badges page.
---
namespace: aiwg
name: aiwg-regenerate-legacy
platforms: [all]
kernel: true
description: Regenerate provider startup context using the legacy inline compatibility branch
commandHint:
argumentHint: "[--provider <name>] [--dry-run]"
allowedTools: Bash, Read
model: haiku
category: maintenance
modelRole: efficiency
modelTier: economy
---
# Regenerate Legacy Inline Context
Use this branch only for compatibility with a provider or project that still requires AIWG context embedded directly in its startup file.
The deterministic command is:
```bash
aiwg regenerate --full-inject [--provider <name>] [--dry-run]
```
The CLI writes `<!-- BEGIN AIWG -->` / `<!-- END AIWG -->` markers, preserves operator prose outside managed blocks, backs up changed existing files, and does not create `WORKSPACE.md`. Preview first for established projects.
Return to the canonical graph with [aiwg-regenerate-workspace](../aiwg-regenerate-workspace/SKILL.md).
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
