A migration guide for replacing deprecated Rossum extensions with formula fields and updating serverless hooks to Python 3.12. Serverless hooks are small pieces of Python that run in response to events.

Use it to replace copy, mapping, find-and-replace, and date-calculation extensions, update old Python runtimes, and create an upgrade manifest.

It helps modernize older implementations while recording what changed so the new setup can be checked against the old behavior.

upgrade — Skill for Claude Code by rossumai/claude-marketplace

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 rossumai/claude-marketplace --skill upgrade

Clone the repo

git clone --depth 1 https://github.com/rossumai/claude-marketplace

Made for: Claude Code.

Or install rossum-sa, the plugin that ships this one along with the rest of its 35 skills, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rossumai/claude-marketplace/upgrade/github.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/upgrade)

Your own site

<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/upgrade"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/upgrade/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/rossumai/claude-marketplace/upgrade"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,587 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00090	$0.05587
Opus 5.5	$0.00036	$0.02235
Sonnet 5.5	$0.00018	$0.01117
Haiku 4.5	$0.00009	$0.00559

Measured 1mo ago against content hash 1bf71e61676e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

upgrade 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 1mo 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/rossum-sa/skills/upgrade/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upgrade Rossum Implementation

You are a Rossum.ai Solution Architect upgrading a customer's implementation from deprecated extensions to modern formula fields and bringing serverless function hooks onto the current Python runtime.

Path or context: $ARGUMENTS

The output of this skill is the upgrade manifest (UPGRADE-<project>-<date>.yaml + rendered .md) plus the in-place migration-trace breadcrumbs. Downstream skills (test-behavioral-equivalence, analyze, review) read these to know what changed and how to verify it. See:

manifest.md — manifest schema and validation rules.
migration-trace.md — the //-comment and migration-trace: header convention, plus the grammar the test-behavioral-equivalence skill's parser expects.

Scope

This upgrade covers value transformations, date calculations, and Python runtime versions — extensions that copy, transform, map field values, compute dates, plus any function hook pinned to an outdated Python runtime:

Deprecated Extension / Runtime	Replacement	Why
Copy & Paste Values	Formula field	Extension is deprecated and no longer maintained
Find & Replace Values	Formula field	Extension is deprecated and no longer maintained
Value Mapping	Formula field	Formula fields are simpler, faster, and version-controlled
Date Calculation	Formula field	Extension is deprecated and no longer maintained
Function hook `config.runtime` = `python3.8` / `python3.9` / `python3.10` / `python3.11`	`python3.12`	Older runtimes are deprecated on the Rossum platform

Phase 1: Find Deprecated Extensions

Use the provided path (or current directory if none given). Refer to skills/__shared/discovery-checklist.md for glob patterns.

Find all hook JSON files: **/hooks/*.json
Identify deprecated extensions by grepping hook files for these patterns:
- Names containing: Copy, Paste, Find, Replace, Value Mapping, Mapping, Date Calculation, Date Calc
- Hook URLs containing: copy-paste, find-replace, value-mapping, date-calculation 2b. A Business Rules Validation hook (a checks[] config) is a common port target for native Rules and is recorded by the hook_to_rule axis, but it is not deprecated and the patterns above do not find it. If one is in scope for the engagement, discover it separately (grep hook settings for "checks") and port it per business-rules-reference → Porting expressions between engines; it is out of scope for this skill's automatic sweep.
Identify outdated Python runtimes on function hooks by grepping hook files for "runtime": and collecting every value that is not "python3.12" (e.g., python3.8, python3.9, python3.10, python3.11). Only hooks of "type": "function" have a runtime field — webhook/connector hooks do not.
For each match, read the full hook JSON — especially settings (the transformation rules) and queues (which queues use it). For function hooks, also read the corresponding .py file(s) so you can flag any code that won't run on 3.12.
Find the schema for each affected queue (**/schema.json in the matching queue directory) so you know what fields exist

Read the full file on GitHub · 317 lines

Files

What ships with it

2 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.

1mo ago Changed · +10 lines 1bf71e61676e
2mo ago First seen · 307 lines · 90 tokens per session scan A 56a153ddbe41

Subscribe to this mod's changes

upgrade is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 90 tokens to every session and 5,587 once invoked, about $0.0004 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 2026-08-31.

Languages Python

upgrade next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
upgraderossumai/claude-marketplace	Skill	5	5d ago	MIT	A	90	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	57k	2d ago	MIT	A	44	Claude Code
pennylaneK-Dense-AI/scientific-agent-skills	Skill	57k	2d ago	MIT	A	74	Claude Code
holoscan-install-wheelNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	34	Claude Code, Codex
python-engineering-guidelinesanywhere-labs/Agents-Anywhere	Skill	3.3k	yesterday	Apache-2.0	A	75	Codex
future-self-liteTHU-MAIC/OpenMAIC	Skill	43k	today	MIT	A	20	Claude Code, Codex
rocm-kernelshuggingface/kernels	Skill	787	yesterday	Apache-2.0	A	93	Claude Code