What is test-behavioral-equivalence?

A procedure for checking that a changed Rossum implementation produces the same document results as the previous version. It saves outputs from an old environment, replays the same documents in a new one, and compares the results.

Use it to compare old and upgraded Rossum environments using representative documents, with confirmation required before remote test data is created or changed.

It detects behavior changes after upgrades or refactoring when the intended outcome was to preserve existing processing.

test-behavioral-equivalence — Skill for Claude Code by rossumai

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 test-behavioral-equivalence

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 33 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/test-behavioral-equivalence/github.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/test-behavioral-equivalence)

Your own site

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

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 10,381 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 warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 33
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Rogue Agent · line 155
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

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	$0.00106	$0.10381
Opus 5	$0.00053	$0.05190
Sonnet 5	$0.00021	$0.02076
Haiku 4.5	$0.00011	$0.01038

Measured 12d ago against content hash ac8b18f2ed39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

test-behavioral-equivalence 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 12d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/apply_patch_plan.py, scripts/build_patch_plan.py, scripts/capture_snapshots.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.

plugins/rossum-sa/skills/test-behavioral-equivalence/SKILL.md · 537 lines

How it starts

The opening of the file, as written. The whole thing — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Behavioral Equivalence of a Rossum Implementation

You are a Rossum.ai Solution Architect verifying that a change to a customer's implementation preserves behavior. The core goal is behavioral equivalence: for a representative corpus of documents, the upgraded implementation should produce the same observable state as the original.

Prerequisites: two coexisting Rossum environments — a source running the old config (the behavioral ground truth) and a target running the upgraded config (the replay target) — plus a local repo holding the upgraded files for Phase 1 static checks and migration-trace extraction. See Phase 0e for setup detail.

Path or context: $ARGUMENTS

Safety: Remote API Confirmation Gate

Present exactly what will be done — tool name, target environment, what gets created/changed/deleted
Wait for explicit user confirmation — do NOT batch multiple write operations into one approval
Never proceed without a clear "yes" from the user

This applies to:

Creating the test queue via the Rossum API
Uploading documents to the test queue
PATCHing annotation fields during replay
Confirming annotations during replay
prd2 push commands (scoped via -io to indexed files only — confirm the file list before executing)

Read-only operations are fine without confirmation: listing hooks/schemas/annotations, rossum_get_document, rossum_get_annotation_content, data_storage_find/aggregate for reads.

Never run replay against a production queue. The test queue and any replay annotations must live in a dedicated test queue or sandbox environment.

How to Use This Skill

Five phases. Phase 0 decides what testing is needed; phases 1-4 produce the test report. Use tasks to track progress.

Phase	Reference Skills
0 — Scope	Change manifest from `upgrade`, `__shared/discovery-checklist.md`
1 — Static Validation	`rossum-reference`, `txscript-reference`
2 — Build Corpus	`rossum-reference` (annotation lifecycle), `prd-reference`
3 — Replay	`txscript-reference`, `mdh-reference`, `export-pipeline-reference`
4 — Diff & Report	—

Read the full file on GitHub · 537 lines

Files

What ships with it

7 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.

12d ago First seen · 537 lines · 106 tokens per session scan A ac8b18f2ed39

Subscribe to this mod's changes

test-behavioral-equivalence is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 10,381 once invoked, about $0.0005 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

test-behavioral-equivalence