txscript-reference

txscript-reference is a skill for Claude Code from rossumai/claude-marketplace. It costs 170 tokens per session (784 once invoked), scanned A, original, MIT.

A reference guide for writing Rossum field expressions: small Python programs or conditions that read and calculate values from document data. It covers server-triggered hooks, validation rules, and formulas for calculated fields.

In plain words
What is it for?
Use it when building webhook-triggered Python hooks, conditions that decide whether Rossum rules run, or formulas that derive schema-field values.
Why use it?
It helps developers use the right syntax and data context for each Rossum feature, avoiding errors caused by treating these three expression types as identical.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the rossum-sa plugin — 35 skills, 4 hooks shipped together

Good fit Use it when building webhook-triggered Python hooks, conditions that decide whether Rossum rules run, or formulas that derive schema-field values.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rossumai/claude-marketplace/txscript-reference
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 txscript-reference
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.

agentmods badge for txscript-reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/rossumai/claude-marketplace/txscript-reference/github.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/txscript-reference)
Your own site
<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/txscript-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/txscript-reference/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 txscript-reference

Your own site · 80×15
<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/txscript-reference"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/txscript-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 784 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 $0.00170 $0.00784
Opus 5.5 $0.00068 $0.00314
Sonnet 5.5 $0.00034 $0.00157
Haiku 4.5 $0.00017 $0.00078

Measured 1mo ago against content hash edc7471cdfd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

txscript-reference 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/txscript-reference/SKILL.md · 34 lines

What it actually says

Rossum Field-Expression Reference: TxScript, Rules, Formulas

This skill is the practical reference for every Rossum surface that runs a Python-flavored expression on annotation data:

  1. TxScript serverless hooks (.py files invoked by webhook events) — full Python 3.12, with the TxScript helper class.
  2. Native Rule trigger_condition expressions (POST /v1/rules) — the boolean condition language. The Rule entity, actions[], and FIRE-vs-PASS polarity are documented in the business-rules-reference skill.
  3. Schema-field formulas (formulas/<field_id>.py next to schema.json) — multi-line Python expressions where the last expression is the field's value.

All three share the same Python expression sublanguage (operators, comparisons, helpers like default_to / is_empty) but the evaluation context differs (event-driven hook vs. validation-time rule vs. derived-field formula). See reference.md for the full reference; the rest of this SKILL.md indexes when to consult what.

IMPORTANT — editing rule:

  • For hook code: always edit the .py file next to the hook JSON. Never edit the code field inside the hook's .json. prd2 extracts hook code into .py files on pull and merges it back on push.
  • For formulas: always edit formulas/<field_id>.py next to schema.json. Never edit the formula property inside schema.json directly. prd2 handles the round-trip.
  • For Rules: edit the rule JSON directly (trigger_condition is a string field, not extracted into a .py).

Use this knowledge when:

  • Writing or debugging a TxScript serverless hook (the original audience)
  • Writing a native Rule trigger_condition expression (the Rule entity and actions[] live in business-rules-reference)
  • Authoring a schema-field formula (single-expression or multi-line)
  • Working out when a formula (re)evaluates — in particular that a plain queue move carries values across without recomputing them
  • Looking up common schema field IDs and their conventions

Cross-references:

  • business-rules-reference covers the rule/validation feature: the native Rule entity, actions[], and FIRE-vs-PASS polarity, plus the legacy Business Rules Validation extension and its own {field}-brace expression engine. Its Porting expressions between engines section is the one to read before translating any legacy expression into a trigger_condition or a formula — the observed defects are all value-semantics mismatches invisible in the source text.
  • rossum-reference covers the platform overall.
  • prd-reference covers the local file layout and prd2 push/pull workflow.
Files

What ships with it

1 file 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. 1mo ago Changed · +1 lines edc7471cdfd4
  2. 2mo ago First seen · 33 lines · 170 tokens per session scan A 8ccf16ded44b

Subscribe to this mod's changes

txscript-reference is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session and 784 once invoked, about $0.0007 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.

Related

txscript-reference compared with skills from other repositories

txscript-reference next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
txscript-referencerossumai/claude-marketplaceSkill5yesterdayMITA170Claude Code
mcp-tool-developersickn33/agentic-awesome-skillsSkill50ktodayMITA38Claude Code
mem0-oss-to-platformmem0ai/mem0Skill69k6d agoApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2ktodayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2ktodayMITA46Claude Code
api-designericrisco/rsc-harnessSkill590yesterdayMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill260yesterdayMITA106Claude Code