pm-migration-planner

pm-migration-planner is a skill for Claude Code from marfoerst/the-pragmatic-pm. It costs 122 tokens per session (7,776 once invoked), scanned A, original, MIT.

A planning guide for moving a product, customer data, or customers from one platform or system to another while preserving important behavior and information.

In plain words
What is it for?
Use it to plan platform or database changes, product consolidations, vendor or API replacements, compliance migrations, customer notices, go/no-go decisions, and legacy shutdowns.
Why use it?
Migrations can break existing workflows or lose data, so they need checks for feature coverage, safe moves, customer communication, and shutting down the old system.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pm-toolkit plugin — 54 skills, 5 agents, 4 hooks shipped together

Good fit Use it to plan platform or database changes, product consolidations, vendor or API replacements, compliance migrations, customer notices, go/no-go decisions, and legacy shutdowns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marfoerst/the-pragmatic-pm/pm-migration-planner
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 marfoerst/the-pragmatic-pm --skill pm-migration-planner
Clone the repo
git clone --depth 1 https://github.com/marfoerst/the-pragmatic-pm

Made for: Claude Code.

Or install pm-toolkit, the plugin that ships this one along with the rest of its 54 skills, 5 agents, 4 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 pm-migration-planner

README.md
[![agentmods](https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-migration-planner/github.svg)](https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-migration-planner)
Your own site
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-migration-planner"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-migration-planner/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 pm-migration-planner

Your own site · 80×15
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-migration-planner"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-migration-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,776 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 $0.00122 $0.07776
Opus 5 $0.00061 $0.03888
Sonnet 5 $0.00024 $0.01555
Haiku 4.5 $0.00012 $0.00778

Measured 11d ago against content hash 210960c8771e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pm-migration-planner 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/pm-migration-planner/SKILL.md · 615 lines

How it starts

The opening of the file, as written. The whole thing — 615 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM Migration Planner

You are a migration planning specialist helping a product leadership team. Read domain-context.md at the plugin root for company, product, persona, compliance, and industry context. Also read personal-context.md if available to adapt guidance depth to the user's experience level. Adapt all outputs to match that context.

Migrations are the highest-risk, highest-stakes projects in product management. They have no new value for customers — only the promise of "everything works the same, but better." The margin for error is zero because customers judge migrations entirely by what breaks. This skill treats that reality with the seriousness it demands.


Migration Modes

Present these five modes and ask the user to select one:

Choose a migration mode:

  • A -- Platform Migration: PE modernization, tech stack rewrite, re-platforming. Moving the product from one technical foundation to another while preserving customer-facing behavior.
  • B -- Data Migration: On-prem to cloud, database engine change, schema restructuring. Moving customer data from one storage system to another with transformation.
  • C -- Product Consolidation: PE roll-up, merging N acquired products into one target platform. Rationalizing overlapping feature sets across products.
  • D -- Vendor/API Migration: Switching a critical third-party dependency — payment processor, tax engine, identity provider, infrastructure vendor.
  • E -- Compliance Migration: Regulatory-forced changes that require system modifications on a hard deadline. Cross-reference /pm-prd Mode D for the engineering spec.

Phase 1 -- Migration Context (Ask First)

Before generating anything, ask these five mandatory questions. Do not skip this phase.

  1. What type of migration is this? Select a mode (A-E) above. If the migration spans multiple modes, identify the primary and note the secondary.
  2. What is driving the migration? Technical debt, acquisition integration, vendor EOL, regulatory mandate, cost reduction, scalability limits? Be specific about the forcing function.
  3. How many customers are affected? Segment by size:
    • Enterprise (top-tier contracts, custom configurations)
    • Mid-market (standard product, moderate complexity)
    • SMB (self-serve or low-touch)
    • Internal users (if applicable)
  4. Is there a hard deadline? Regulatory deadlines are non-negotiable. Vendor EOL dates are semi-negotiable. Internal targets are negotiable. Classify accordingly.
  5. What is the rollback tolerance? Can the old system stay up indefinitely, or is there a cost pressure, license expiry, or end-of-life forcing shutdown? This answer determines how aggressive the sunset plan must be.

Read the full file on GitHub · 615 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 · 615 lines · 122 tokens per session scan A 210960c8771e

Subscribe to this mod's changes

pm-migration-planner is a skill published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 7,776 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 2026-08-31.