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.
npx skills add build-with-dhiraj/ai-workflow-framework-portability-kit --skill mac-migrationgit clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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.
[](https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/mac-migration)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/mac-migration"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/mac-migration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/mac-migration"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/mac-migration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00221 | $0.02816 |
| Opus 5.5 | $0.00088 | $0.01126 |
| Sonnet 5.5 | $0.00044 | $0.00563 |
| Haiku 4.5 | $0.00022 | $0.00282 |
Grade B, and why
mac-migration scanned grade B with 1 finding 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
5. **Done means redundant, not "it works."** A single Mac + a soon-to-be-deleted cloud bundle is the *same* single point of failure that motivated the migration — worse if it's a corporate/MDM-managed machine that IT can How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mac-to-Mac Migration (same Claude login)
The one truth that changes everything
Signing into Claude on the new Mac restores your account and subscription — nothing else. Your skills, agents, MCP server definitions, plugins, chat history, and all project data are local files (mostly under ~/.claude, ~/.agents, and your code folders). If the old Mac is wiped before those are captured, they are gone. So this is not "zip and hope" — it is a deliberate capture → verify → restore → reconcile project.
Two facts shape the entire approach:
- The new Mac's username is usually different (
pw→dhiraj,pranav, etc.). Every absolute/Users/<old>path must be rewritten. If you can set the new account's short name to match the old one, you delete this entire problem — recommend it early. - The two Macs are rarely online at once, so Migration Assistant over the network often isn't an option. A checksummed archive bundle on cloud/external storage is the reliable path.
Step 0 — figure out which side the user is on, and route
- On the OLD Mac (still have it): you are doing Phase 1 — Prepare & Back Up. Read
references/old-mac-prep.mdand drivescripts/migrate-out.sh. There may be a hard deadline (device return/reset) — establish it and work backward. - On the NEW Mac (old one gone/wiped): you are doing Phase 2 — Restore & Reconcile. Read
references/new-mac-restore.mdand drivescripts/migrate-in.sh. - Debugging a half-done move ("chats say working-directory-not-found", "my skills vanished"): jump to the reconciliation sections in
references/new-mac-restore.md— this is almost always stale/Users/<old>paths in session metadata or broken skill symlinks.
Always confirm the old and new usernames (whoami, echo $HOME) before touching path-rewrite logic.
The five non-negotiable doctrines
These are the hard-won lessons. Violate them and data is silently lost.
- Extract, never
git clone. Restore every project by extracting its archive with.git/intact — not by cloning from GitHub. Cloning gets the code but silently drops gitignored data: Obsidian/RAG vaults,.lancedbvector indexes, git stashes, un-pushed commits, and repos with no remote at all. Those exist only inside the archive. (Clone is a fallback only for a repo that is verified clean and fully pushed.)
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 86 lines · 221 tokens per session scan B 8ef6f75e71b0
mac-migration is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 21d ago), licensed MIT. It adds 221 tokens to every session and 2,816 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other skills, from other repositories
skill-creator
Create new skills (SKILL.md files), modify and improve existing skills, and design skill descriptions for accurate triggering. Use when the user wants to create a new skill from scratch, edit an existing skill, optimize a skill's description, or convert a workflow they just demonstrated into a reusable skill.
huggingface-community-evals
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .evalresults publication, or community-evals automation.
work-log-codex
A workflow for turning Codex and Claude Code session records into readable Markdown work logs. It can organize activity by project and date range, such as today, this week, or a custom period.
knowledge-transfer
Use when a colleague is leaving a project and must hand over knowledge, or when someone new joins a project and receives handover.zip or a handover/ folder. Two phases: export (analyze project + agent project memories from Claude, Codex, or another assistant, then produce a transferable handover.zip archive containing…
hf-cloud-python-env-setup
Create an isolated Python environment with a compatible Python version and boto3 for SageMaker or AWS automation. Use before executing AWS Python code; do not use for general Python environment setup.
pith
Adaptive output compression. Three levels: precise (no filler), lean (default, drop articles/fragments), ultra (maximum — abbreviate, structure, arrows). Activate: /pith | /pith precise | /pith lean | /pith ultra | /pith off.