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.
npx skills add hoanghaoha/survy-agent-skills --skill questionnaire-readinggit clone --depth 1 https://github.com/hoanghaoha/survy-agent-skillsWrote 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.
[](https://agentmods.dev/skills/hoanghaoha/survy-agent-skills/questionnaire-reading)<a href="https://agentmods.dev/skills/hoanghaoha/survy-agent-skills/questionnaire-reading"><img src="https://agentmods.dev/badge/skills/hoanghaoha/survy-agent-skills/questionnaire-reading/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.
<a href="https://agentmods.dev/skills/hoanghaoha/survy-agent-skills/questionnaire-reading"><img src="https://agentmods.dev/badge/skills/hoanghaoha/survy-agent-skills/questionnaire-reading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00129 | $0.01812 |
| Opus 5.5 | $0.00052 | $0.00725 |
| Sonnet 5.5 | $0.00026 | $0.00362 |
| Haiku 4.5 | $0.00013 | $0.00181 |
Grade A, and why
questionnaire-reading 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Questionnaire Reading Skill
This skill converts a raw questionnaire design document into a structured
questionnaire-design.md file. The output becomes the authoritative reference
for survey structure, routing logic, and metadata — enabling an AI agent to
understand the data before writing any survy code.
1. Input Formats
Accept any of the following:
| Format | How to read |
|---|---|
.docx |
Use python-docx (pip install python-docx) to extract paragraphs and tables |
.xlsx / .xls |
Use openpyxl (pip install openpyxl) or polars.read_excel() to iterate rows |
.pdf |
Use pdfplumber (pip install pdfplumber) to extract text page by page |
.txt / .md |
Read directly — plain text, no library needed |
Always inspect the raw content first before deciding on a parsing strategy. Questionnaire documents vary widely; read several rows/paragraphs to detect the layout pattern before extracting.
2. Concepts to Extract
For each question, extract:
| Field | Description |
|---|---|
| Question ID | Short code used in data (e.g. Q1, S2, D3). If not present, assign sequentially. |
| Label / Text | The full question wording shown to respondents. |
| Type | Single (one answer), Multi (multiple answers), Open (free text), Number, Grid. |
| Options | Answer choices with their codes/numbers. Capture exactly as designed. |
| Logic | Routing instruction — who sees this question. See Section 3. |
| Terminate | Flag if any option ends the interview (-> Terminate respondent). |
3. Logic / Routing Rules
Questionnaire logic is the most important thing to capture accurately. Common patterns and how to write them in the output:
| Design wording | Output phrasing |
|---|---|
| "Ask all" / "All respondents" | Logic: All respondents |
| "Ask if Q2 = Yes" / "If Q2 = 1" | Logic: Ask if Q2 == 1 (Yes) |
| "Ask if Q3 = 1 or 2" | Logic: Ask if Q3 == 1 (Cat) OR Q3 == 2 (Dog) |
| "Skip to Q5 if Q4 = No" | Logic: Ask if Q4 != 2 (No) |
| "Ask for all non-terminated" | Logic: Ask for all respondents (who are not terminated) |
| "Ask if Q1 is answered" | Logic: Ask if Q1 is not empty |
| Grid sub-questions | Logic: Same as parent grid question |
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.
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.
- 2mo ago First seen · 198 lines · 129 tokens per session scan A 27fc38152545
questionnaire-reading is a skill published in the GitHub repository hoanghaoha/survy-agent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 129 tokens to every session and 1,812 once invoked, about $0.0005 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.
questionnaire-reading compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| questionnaire-readinghoanghaoha/survy-agent-skills | Skill | 2 | 6mo ago | MIT | A | 129 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | today | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | today | Apache-2.0 | A | 68 | Claude Code |
| report-to-pdfasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 17 | Claude Code, Codex |
| artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 54 | Claude Code, Codex |