migrate-placements

migrate-placements is a skill for Claude Code from adaptyteam/adapty-skills. It costs 130 tokens per session (9,868 once invoked), scanned A, original, MIT.

A migration workflow for moving an app from paywall placements to Flow Builder flows. It creates new flow placements while leaving the existing paywall placements in place.

In plain words
What is it for?
Use it to migrate placements across apps or paywalls when moving to Flow Builder flows.
Why use it?
It helps handle a bulk switch without replacing or removing the current placements. This allows the new setup to be created alongside the old one.

Skill for Claude Code

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

Part of the adapty-skills plugin — 13 skills shipped together

Good fit Use it to migrate placements across apps or paywalls when moving to Flow Builder flows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adaptyteam/adapty-skills/migrate-placements
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 adaptyteam/adapty-skills --skill migrate-placements
Clone the repo
git clone --depth 1 https://github.com/adaptyteam/adapty-skills

Made for: Claude Code.

Or install adapty-skills, the plugin that ships this one along with the rest of its 13 skills.

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-placements

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/adaptyteam/adapty-skills/migrate-placements"><img src="https://agentmods.dev/badge/skills/adaptyteam/adapty-skills/migrate-placements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,868 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 $0.00130 $0.09868
Opus 5.5 $0.00052 $0.03947
Sonnet 5.5 $0.00026 $0.01974
Haiku 4.5 $0.00013 $0.00987

Measured 6d ago against content hash b62b84d6522a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

migrate-placements 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/migrate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugin/skills/migrate-placements/SKILL.md · 659 lines

How it starts

The opening of the file, as written. The whole thing — 659 lines — stays where its author put it; the contents beside it link to each section on GitHub.

migrate-placements

How you sound

Every line the user reads, the fixed blocks included:

  • "I" for what you do, "you" for what they do. Lead with the result; end on one next step. No opener, no recap of their request.
  • Bold at most one thing per block. A fixed block's heading is that one thing; labels such as App, Flows or Permanent stay plain, and so do the route names in a list of options (Reuse, Convert, Build, Stub) — a list of four bold lead-ins is four bolds, not one.
  • Raw values only when the user will type them or see them elsewhere. A placement's developer ID goes in code formatting — they type it into their app. Name an app by its title and a flow by its name, with its last-edited date when several share a name, and link the flows page; never an app or flow UUID. Counts and statuses are plain words ("1, now published"), not code.
  • Ask only what changes the plan. If every answer to a question gives the same result, say so in one line instead of asking it.
  • Say each thing once. What the approval gate said, the final report does not repeat.
  • Full, clickable links. Reply in the user's language, the fixed blocks too.

What this does, and what it cannot do

For an Adapty docs page this skill does not link — how placements, audiences or flows behave in the dashboard — use the adapty-docs skill to find it. Never assemble a docs URL from a topic name.

Two facts decide the whole shape of this skill, and both are measured (api-surface.md):

A placement's content type cannot be changed after creation. placements update with a flow audience on a paywall placement is refused — Placement type can not be changed. — on an environment that has the audience union deployed, so this is the backend's rule and not a missing CLI feature. There is no conversion. Every migration is a placements create, and the existing paywall placement stays exactly as it is.

Read the full file on GitHub · 659 lines

Files

What ships with it

3 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.

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. 6d ago Changed · +6 lines b62b84d6522a
  2. 21d ago Changed · +22 lines 287d32b77364
  3. 1mo ago Changed · -22 lines 67fef2494d3f
  4. 1mo ago Changed 845bb047faa4
  5. 1mo ago Changed · +3 lines 8473a846ec91
  6. 1mo ago Changed · +6 lines 8535b9f382c6
  7. 1mo ago First seen · 644 lines · 130 tokens per session scan A c1cff0546574

Subscribe to this mod's changes

migrate-placements is a skill published in the GitHub repository adaptyteam/adapty-skills (6 stars, last pushed today), licensed MIT. It adds 130 tokens to every session and 9,868 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-10.