record-upgrade-instructions

record-upgrade-instructions is a skill for Claude Code, Codex from prisma/prisma-next. It costs 122 tokens per session (4,023 once invoked), scanned A, original, Apache-2.0.

A workflow for documenting how users and extension authors should update code after a breaking Prisma Next change. It records these instructions in published upgrade skills.

In plain words
What is it for?
It helps maintainers add migration steps for each breaking change and publish them for Prisma Next users and extension authors.
Why use it?
It prevents downstream projects from guessing how to translate their code after framework changes.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/prisma/prisma-next/record-upgrade-instructions
Any agent
npx skills add prisma/prisma-next --skill record-upgrade-instructions
Clone the repo
git clone --depth 1 https://github.com/prisma/prisma-next

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.

agentmods badge for record-upgrade-instructions

README.md
[![agentmods](https://agentmods.dev/badge/skills/prisma/prisma-next/record-upgrade-instructions.svg)](https://agentmods.dev/skills/prisma/prisma-next/record-upgrade-instructions)
Your own site
<a href="https://agentmods.dev/skills/prisma/prisma-next/record-upgrade-instructions"><img src="https://agentmods.dev/badge/skills/prisma/prisma-next/record-upgrade-instructions.svg" alt="Measured on agentmods" 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 4,023 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.04023
Opus 5 $0.00061 $0.02011
Sonnet 5 $0.00024 $0.00805
Haiku 4.5 $0.00012 $0.00402

Measured 2d ago against content hash 5e6b46fbc311, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

record-upgrade-instructions 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 2d 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-contrib/record-upgrade-instructions/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Record upgrade instructions

This skill fires on PRs inside this repo that make a breaking change to Prisma Next. It walks you through adding a per-transition upgrade-instructions entry in the right published skill package(s) — so downstream users and extension authors can run the matching agent flow to migrate their code automatically.

The published skills you will be authoring entries into:

  • skills/upgrade/prisma-next-upgrade/ — distributed via pnpm dlx skills add prisma/prisma-next/skills/upgrade --all. Audience: users of Prisma Next (consumers of the public package API: @prisma-next/postgres, @prisma-next/mongo, the contract files in prisma/, on-disk migration shape).
  • skills/extension-author/prisma-next-extension-upgrade/ — distributed via pnpm dlx skills add prisma/prisma-next/skills/extension-author --all. Audience: authors of Prisma Next extensions (consumers of the framework SPI: @prisma-next/contract, @prisma-next/framework-components, @prisma-next/migration-tools, etc.).

The two skill clusters are independent (no shared content). Cross-audience breaking changes — where the same on-disk transformation applies to both substrates — are recorded separately in each cluster, including duplicated colocated scripts.

When to use

Fire this skill on any PR where:

  • You refactored framework code, then
  • the test suite went red in examples/ and/or packages/3-extensions/, and
  • you fixed those red tests by editing the substrate (not by reverting the framework change).

Those edits to examples/ or packages/3-extensions/ are the signal. The matching test suite would have been red for downstream consumers without an upgrade-instructions entry; the entry's effect on the substrate is the same code translation a downstream consumer will run via the published skill.

If both substrates are touched, both packages need entries (see Cross-audience entries).

Even consumer-invisible-looking diffs need an entry. A change to the format of contract.json / contract.d.ts (or any other emitted artefact) is itself an upgrade instruction — consumers will need to either run a codemod or re-emit. Where the substrate diff is genuinely no-op for consumers (incidental regeneration with no behavioural change), the entry can ship with changes: [] to record that explicitly. There is no carve-out for "generated paths"; any substrate diff requires a record.

Read the full file on GitHub · 160 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. 2d ago First seen · 160 lines · 122 tokens per session scan A 5e6b46fbc311

Subscribe to this mod's changes

record-upgrade-instructions is a skill published in the GitHub repository prisma/prisma-next (419 stars, last pushed 11d ago), licensed Apache-2.0. It adds 122 tokens to every session and 4,023 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 2026-09-03.

Related

Other skills, from other repositories

psl-ast-layers

How to use the PSL syntax tree layers (green tree, red tree, strongly-typed AST classes) correctly. Use for any PSL-related work: PSL interpreters (contract-psl), helpers inside the psl-parser package, the language server, formatters, or anything else that consumes parse() output from @internal/psl-parser.

prisma/orm · 78 tokens

ast-visitor-pattern

Use the frozen-class/visitor pattern for discriminated unions that have multiple dispatch sites. Use when creating a new set of variants (commands, IR nodes, factory calls) that will be switched over in 2+ places, or when refactoring an existing union type that has grown multiple switch sites.

prisma/orm · 65 tokens

no-bare-casts

Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.

prisma/orm · 52 tokens

bumping-biome

Bumps biome package versions (e.g. @biomejs/biome) using pnpm, aligns biome.jsonc files with the new version/s across the repository and runs biome-related checks. Use when required to update biome to a newer version - explicitly or implicitly (e.g. after running pnpm up, pnpm update, pnpm upgrade without specific…

prisma/orm · 96 tokens

create-pr

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.

prisma/orm · 47 tokens

draft-release-notes

Author the committed release-notes file for a Prisma 8 release (stable or 8.0.0-rc.N) by enumerating the merged PRs since the previous release v tag (stable or -rc.N), resolving opaque TML-NNNN: titles via Linear context (never copied verbatim), triaging public-worthiness, and writing categorized notes — breaking…

prisma/orm · 174 tokens