queue-engine-binding

queue-engine-binding is a skill for Claude Code from rossumai/claude-marketplace. It costs 110 tokens per session (1,020 once invoked), scanned A, original, MIT.

A tool for changing which data-extraction engine processes a Rossum queue. A queue is a document-processing workflow, and an extraction engine identifies fields in its documents.

In plain words
What is it for?
Use it to create an engine-bound queue, attach an existing queue to an engine, switch from the generic engine, or revert that binding.
Why use it?
It coordinates the related engine-field, schema, and queue changes so they do not drift apart. It also supports previewing the planned changes and saving a snapshot before applying them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the rossum-sa plugin — 33 skills, 4 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add rossumai/claude-marketplace
Claude Code
/plugin install rossum-sa

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.

agentmods badge for queue-engine-binding

README.md
[![agentmods](https://agentmods.dev/badge/skills/rossumai/claude-marketplace/queue-engine-binding.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/queue-engine-binding)
Your own site
<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/queue-engine-binding"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/queue-engine-binding.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,020 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 $0.00110 $0.01020
Opus 5 $0.00055 $0.00510
Sonnet 5 $0.00022 $0.00204
Haiku 4.5 $0.00011 $0.00102

Measured 5d ago against content hash bb0f417b0e22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

queue-engine-binding 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 5d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (engine_binding.py, tests/test_engine_binding.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/queue-engine-binding/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Queue ↔ Engine Binding

Mode and target: $ARGUMENTS

Reconciles schema datapoints ↔ engine fields ↔ queue binding, then sets queue.engine. Background and binding rules: rossum-sa:rossum-reference → Extraction Engines.

Scope: this skill covers bind-level mode changes (convert/greenfield/attach/revert). For incrementally adding, adjusting, or removing a single field on an ALREADY engine-bound queue, use the MCP tools directly instead — rossum_create_engine_fieldrossum_patch_schema to add (engine field first; dry-run the schema edit with rossum_validate_schema + schema id), the reverse order to remove (rossum_delete_engine_field 409s while the datapoint exists), rossum_patch_engine_field to adjust.

Safety

  • Every mode defaults to dry-run. Show the user the printed plan (engine fields to create, schema changes) and get explicit confirmation before re-running with --execute. Never skip this for production queues.
  • Convert/attach/revert write a pre-state snapshot with --snapshot-dir — always pass it; the snapshot is the revert path.
  • A 403 on engine creation means the org/token lacks the permission — stop and advise the user to contact Rossum support; record which org/role combination failed.

Running

export ROSSUM_TOKEN=<token>
python3 ${CLAUDE_PLUGIN_ROOT}/skills/queue-engine-binding/engine_binding.py \
  convert --base-url https://<org>.rossum.app --queue-id <id> \
  --snapshot-dir ./engine-binding-snapshots
Mode Required args What it does
convert --queue-id Generic-bound queue → new engine: derive engine fields from the schema (pretrained-catalog seeding), clean the schema (rir_field_names: [], normalize ui_configuration, strip disable_prediction), create engine + fields, flip the queue.
greenfield --schema-file --queue-name --workspace-url New queue born engine-bound from a local schema JSON.
attach --queue-id --engine-id Bind to an existing engine; creates only the missing engine fields, then cleans + flips.
revert --queue-id --generic-engine-url Detach to generic engine and restore rir_field_names from pre_trained_field_id mappings (or restore the snapshot schema manually for exact pre-state). Find the --generic-engine-url value in the convert snapshot's pre_queue.json under generic_engine, or in any sibling generic-bound queue's queue.json.

Read the full file on GitHub · 52 lines

Files

What ships with it

5 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. 5d ago First seen · 52 lines · 110 tokens per session scan A bb0f417b0e22

Subscribe to this mod's changes

queue-engine-binding is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It adds 110 tokens to every session and 1,020 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens