surveycto-form-reader

surveycto-form-reader is a skill for Claude Code, Codex from albertotrelles/xlsform-reader. It costs 184 tokens per session (1,830 once invoked), scanned A, original, MIT.

A reader for SurveyCTO and ODK form-definition spreadsheets. SurveyCTO and ODK are tools for building digital surveys, and an XLSForm is the spreadsheet that describes a survey’s questions and rules.

In plain words
What is it for?
Use it to summarize a survey, create a data dictionary, write analysis or cleaning code with the correct field names, and explain when questions appear.
Why use it?
It turns a form spreadsheet into readable information, so you do not have to decode variable names, answer choices, and skip rules manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/albertotrelles/xlsform-reader/surveycto-form-reader
Any agent
npx skills add albertotrelles/xlsform-reader --skill surveycto-form-reader
Clone the repo
git clone --depth 1 https://github.com/albertotrelles/xlsform-reader

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 surveycto-form-reader

README.md
[![agentmods](https://agentmods.dev/badge/skills/albertotrelles/xlsform-reader/surveycto-form-reader.svg)](https://agentmods.dev/skills/albertotrelles/xlsform-reader/surveycto-form-reader)
Your own site
<a href="https://agentmods.dev/skills/albertotrelles/xlsform-reader/surveycto-form-reader"><img src="https://agentmods.dev/badge/skills/albertotrelles/xlsform-reader/surveycto-form-reader.svg" alt="Measured on agentmods" height="20"></a>
Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,830 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 $0.00184 $0.01830
Opus 5 $0.00092 $0.00915
Sonnet 5 $0.00037 $0.00366
Haiku 4.5 $0.00018 $0.00183

Measured 5d ago against content hash e562081afb4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

surveycto-form-reader 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 1 executable file (scripts/parse_form.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.

surveycto-form-reader/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SurveyCTO Form Reader

Purpose

This skill lets you parse a SurveyCTO/ODK form definition spreadsheet (.xlsx) into plain-text CSVs you can read, and gives you the domain knowledge to understand the form's structure, variables, skip logic, choice lists, and repeat groups. With this understanding you can:

  • Summarize the survey instrument (sections, field counts, flow)
  • Generate codebooks / data dictionaries
  • Write analysis code (Stata, Python) using correct variable names and value labels
  • Build data cleaning and high-frequency check scripts informed by form logic
  • Explain what specific variables mean, including their skip conditions

Step 1: Parse the form definition

The form .xlsx cannot be read directly. Run the parser script:

python3 /path/to/this/skill/scripts/parse_form.py "<path_to_form.xlsx>" --outdir /tmp/form_parsed

This produces CSV files in the output directory:

  • survey.csv — all fields, groups, and their properties
  • choices.csv — all choice lists with list_name, value, label
  • settings.csv — form title, form ID, default language, version
  • summary.txt — a human-readable overview of the form

Read summary.txt first for a quick overview, then consult the CSVs as needed for details.

If the script is not at the expected path (e.g., the user installed the skill elsewhere), look for parse_form.py inside a scripts/ folder adjacent to this SKILL.md.

Step 2: Understand the form structure

After parsing, read references/surveycto-form-spec.md (adjacent to this SKILL.md) to understand how to interpret the parsed data. Key concepts:

  • survey sheet: each row is a field. The type column determines what kind of field it is. The name column is the variable name in exported data. label is the question text. relevance is skip logic. constraint restricts valid entries.
  • choices sheet: defines value labels for select_one and select_multiple fields. Linked by list_name.
  • Groups: begin group / end group rows define sections. begin repeat / end repeat define roster/loop structures.
  • Field types: text, integer, decimal, select_one listname, select_multiple listname, date, datetime, geopoint, calculate, note, and more.

Read the full file on GitHub · 166 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.

  1. 5d ago First seen · 166 lines · 184 tokens per session scan A e562081afb4a

Subscribe to this mod's changes

surveycto-form-reader is a skill published in the GitHub repository albertotrelles/xlsform-reader (5 stars, last pushed 5mo ago), licensed MIT. It adds 184 tokens to every session and 1,830 once invoked, about $0.0009 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.