migrate

migrate is a skill for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 123 tokens per session (4,570 once invoked), scanned A, original, MIT.

A migration procedure for moving an existing code repository into a standard `.credo/` folder structure. It also turns scattered project records and open work into Credo work items.

In plain words
What is it for?
Use it when onboarding a legacy repository into Credo, organizing process documents, or converting existing open work into Credo items.
Why use it?
It gives the migration a defined target and steps for preserving requirements, notes, plans, and other project information. This reduces the risk of losing context or creating an inconsistent structure.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the credo plugin — 26 skills, 15 commands, 6 hooks shipped together

Good fit Use it when onboarding a legacy repository into Credo, organizing process documents, or converting existing open work into Credo items.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace
Claude Code
/plugin install credo

Made for: Claude Code.

Or install credo, the plugin that ships this one along with the rest of its 26 skills, 15 commands, 6 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/migrate/github.svg)](https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/migrate)
Your own site
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/migrate"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/migrate/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.

agentmods 80×15 button for migrate

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/migrate"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/migrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,570 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00123 $0.04570
Opus 5 $0.00062 $0.02285
Sonnet 5 $0.00025 $0.00914
Haiku 4.5 $0.00012 $0.00457

Measured 11d ago against content hash e1c89af4ccb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

migrate 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.

plugins/credo/skills/migrate/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

migrate - bring an existing repo into .credo/

A generic, reusable procedure to migrate ANY existing repo into the credo target form. It tells you HOW to reach that end state safely. Everywhere below, <repo> is the target repo and "the user" is its owner. This skill contains no personal, project-specific, or absolute-path data.

Target form: what "conformant" means here (authority)

The binding target form is defined INSIDE this plugin, not by any external design document. At the end of a migration, everything under .credo/ must match:

  • The scaffolded tree produced by "${CLAUDE_PLUGIN_ROOT}/scripts/credo-init.sh" - folder layout and the files it creates (see step 1). That tree is the layout authority.
  • The items skill - the work-item model: folder = status, the lean frontmatter, the body sections, the Definition of Done, and id issuance.
  • The safety skill - the highest-priority filesystem-protection and no-autonomous-installs rules; they bind this whole procedure.
  • The requirements-verbatim skill - the append-only, never-censored requirements log and the strict separation of user-verbatim text from any assistant proposal.
  • The verify skill - what a real (visual, per-viewport) verification is, which governs whether a criterion counts as exercised.
  • The budget skill - budget caps and the commit-identity gate, when a migration run is autonomous and commits anything.

Reference these by name. If any instruction points you at an external "structure design" document, ignore it - the plugin-internal authority above is the target form.

0. What "migration" means (read first)

  • Migration produces the structure-conformant END STATE. At the end, everything in .credo/ matches the target form above: folder layout, file names, frontmatter, and the items model. It is NOT a verbatim copy of the old files under new folders.
  • Loss protection comes from the untouched originals, not from verbatim file names in .credo/. The originals stay exactly where they are until the final step (8), so you may restructure aggressively inside .credo/.
  • "Verbatim" is scoped. Preserve the CONTENT wording of requirements logs and evidence / reports (never rewrite, trim, soften, or censor them - this is the requirements-verbatim rule). File names, placement, frontmatter, and splitting sources into items ARE adapted.

Read the full file on GitHub · 278 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. 11d ago First seen · 278 lines · 123 tokens per session scan A e1c89af4ccb4

Subscribe to this mod's changes

migrate is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed 2d ago), licensed MIT. It adds 123 tokens to every session and 4,570 once invoked, about $0.0006 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 2026-08-30.