What is migrate-claude-project?

A tool that imports a folder of previous Claude work into an Obsidian vault, a local collection of linked notes, and organizes it into PARA notes. PARA is a filing method based on projects, areas, resources, and archives.

Use it to seed an Obsidian vault from a Claude.ai project, Cowork project, or another folder containing past Claude work.

It turns older conversations and project files into organized notes that can be searched and reused instead of leaving them in a separate, hard-to-use folder.

migrate-claude-project — Skill for Claude Code and Codex by jenningsal

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.

Any agent

npx skills add jenningsallen-art/second-brain-os --skill migrate-claude-project

Clone the repo

git clone --depth 1 https://github.com/jenningsallen-art/second-brain-os

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jenningsallen-art/second-brain-os/migrate-claude-project/github.svg)](https://agentmods.dev/skills/jenningsallen-art/second-brain-os/migrate-claude-project)

Your own site

<a href="https://agentmods.dev/skills/jenningsallen-art/second-brain-os/migrate-claude-project"><img src="https://agentmods.dev/badge/skills/jenningsallen-art/second-brain-os/migrate-claude-project/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jenningsallen-art/second-brain-os/migrate-claude-project"><img src="https://agentmods.dev/badge/skills/jenningsallen-art/second-brain-os/migrate-claude-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,936 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00179	$0.02936
Opus 5	$0.00089	$0.01468
Sonnet 5	$0.00036	$0.00587
Haiku 4.5	$0.00018	$0.00294

Measured 11d ago against content hash 104505de32dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

migrate-claude-project 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 11d 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.

skills/migrate-claude-project/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Migrate Claude Project

The seeding skill that turns "I have months of Claude.ai work I'm not using" into "my vault is populated and load-bearing from day one." Run once per old project folder the user wants to bring across. Designed to follow /personalize-second-brain in the adopter's setup flow, but works any time.

This is the second-most-important skill in the package after personalize-second-brain. Without it, new adopters start with an empty vault and the morning brief has nothing to read. With it, the vault feels like home from the first day.

When to invoke

Triggers:

Slash command: /migrate-claude-project (uses cwd as the source folder) or /migrate-claude-project /absolute/path
Phrases: "migrate this folder", "import my Claude project", "seed my vault from old Claude work", "bring this project into my vault"

Skip if:

The user has no prior Claude work and is starting fresh — tell them this skill is optional
The source folder is already in the vault (would create circular structure)
The source folder appears empty (no .md, no code files, no .claude/) — say so and exit

Operating Modes

Mode	Trigger	Behavior
First-run (default)	No matching `source-folder: <path>` found in vault frontmatter	Run the full inventory + confirm + generate flow.
Re-run / additive	One or more notes in vault have `source-folder: <path>` matching this folder	Show the user what's already imported, ask what to do: • Add new — only generate notes for files not already represented • Refresh all — back up existing notes (`.backup-YYYYMMDD-HHMM.md`), regenerate from scratch • Cancel*
Dry-run	`--dry-run` flag	Run inventory + show the planned notes (filenames, folders, ~3-line previews) without writing. Useful for the coached install demo.

Step 1 — Inventory

Read everything in the source folder. Do not generate notes yet.

List all files and directories recursively. Note types: .md, .py / .js / .tsx / etc., .json, .csv, plain text, images, anything else.
If a .claude/ directory exists, read the conversation history files in it. These often contain the load-bearing decisions and context that aren't in the code.
If a .gitignore or .git/ exists, ignore the latter and respect the former.
Skip binary blobs, lock files, node_modules/, __pycache__/, build outputs.

Read the full file on GitHub · 218 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.

11d ago First seen · 218 lines · 179 tokens per session scan A 104505de32dc

Subscribe to this mod's changes

migrate-claude-project is a skill published in the GitHub repository jenningsallen-art/second-brain-os (2 stars, last pushed 1mo ago), licensed MIT. It adds 179 tokens to every session and 2,936 once invoked, about $0.0009 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 2026-08-31.

Documents Memory and context

obsidian

Obsidian vault: search/read/write notes, backlinks, Bases, Canvas.

steipete/agent-scripts · 19 tokens

loopx-doc-registry

Use when a connected LoopX project is asked to read, remember, record, index, register, or use a durable project material such as a Lark/wiki/design doc, research note, SOP, owner packet, migration report, benchmark paper, or external material source. Use even when the user does not mention LoopX or doc registry.

huangruiteng/loopx · 74 tokens

migrate-claude-project