migrate-workspace

migrate-workspace is a skill for Claude Code, Codex from jmagly/aiwg. It costs 26 tokens per session (1,181 once invoked), scanned A, original, MIT.

A migration tool that moves an old single-framework .aiwg layout to a multi-framework layout while creating a backup.

In plain words
What is it for?
Use it to preview or perform the layout migration, check whether migration is needed, and skip confirmation when appropriate.
Why use it?
It updates the project structure without losing the original files if something goes wrong.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/jmagly/aiwg/migrate-workspace
Any agent
npx skills add jmagly/aiwg --skill migrate-workspace
Clone the repo
git clone --depth 1 https://github.com/jmagly/aiwg

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for migrate-workspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/jmagly/aiwg/migrate-workspace.svg)](https://agentmods.dev/skills/jmagly/aiwg/migrate-workspace)
Your own site
<a href="https://agentmods.dev/skills/jmagly/aiwg/migrate-workspace"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/migrate-workspace.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.01181
Opus 5 $0.00013 $0.00590
Sonnet 5 $0.00005 $0.00236
Haiku 4.5 $0.00003 $0.00118

Measured 3d ago against content hash d8d92476618b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

migrate-workspace scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agentic/code/addons/aiwg-utils/skills/migrate-workspace/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Migrate Workspace

You upgrade the .aiwg/ directory from the old single-framework layout to the new multi-framework layout, moving artifacts into framework-scoped subdirectories. A backup is always created before any changes are applied.

Triggers

Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):

  • "upgrade my aiwg structure" → run migration
  • "move to multi-framework layout" → run migration
  • "preview workspace migration" → dry-run only
  • "what would migrate?" → dry-run only

Trigger Patterns Reference

Pattern Example Action
Full migration "migrate my workspace" Run aiwg migrate-workspace
Dry run "preview the workspace migration" Run aiwg migrate-workspace --dry-run
Forced "migrate workspace, skip confirmation" Run aiwg migrate-workspace --yes
Check needed "do I need to migrate?" Run aiwg migrate-workspace --dry-run

Behavior

When triggered:

  1. Always dry-run first unless the user explicitly confirms or passes --yes:

    • Run aiwg migrate-workspace --dry-run to show what would move.
    • Report the planned changes to the user.
    • Ask for confirmation before proceeding.
  2. Extract arguments:

    • Is --dry-run requested? Report only, no changes.
    • Has the user already confirmed? Use --yes to skip the interactive prompt.
    • Is there a specific backup path? (optional)
  3. Run the appropriate command:

    # Preview only — no changes
    aiwg migrate-workspace --dry-run
    
    # Full migration (prompts for confirmation)
    aiwg migrate-workspace
    
    # Full migration, skip prompt
    aiwg migrate-workspace --yes
    
  4. What the migration does:

    • Creates a timestamped backup at .aiwg/.backup-<timestamp>/
    • Creates framework-scoped subdirectories under .aiwg/frameworks/<name>/
    • Moves existing flat artifacts into the appropriate scoped location
    • Updates .aiwg/frameworks/registry.json
    • Leaves a MIGRATION.md log at .aiwg/ root

Read the full file on GitHub · 160 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 160 lines · 26 tokens per session scan A d8d92476618b

Subscribe to this mod's changes

migrate-workspace is a skill published in the GitHub repository jmagly/aiwg (209 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,181 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.