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 Firstp1ck/pi-coding-agent-forge --skill questionnairegit clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forgeWrote 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/firstp1ck/pi-coding-agent-forge/questionnaire)<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/questionnaire"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/questionnaire/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/firstp1ck/pi-coding-agent-forge/questionnaire"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/questionnaire.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00110 | $0.01600 |
| Opus 5.5 | $0.00044 | $0.00640 |
| Sonnet 5.5 | $0.00022 | $0.00320 |
| Haiku 4.5 | $0.00011 | $0.00160 |
Grade A, and why
questionnaire 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Questionnaire
Ask related structured questions in one native dialog flow and read the answers back as stable IDs.
The questionnaire tool runs Pi's native selector and text-input dialogs sequentially. It works in the TUI (Up/Down + Enter) and in the WebUI (options are ordinary clickable buttons).
When to use
Use questionnaire when:
- two or more related choices must be settled before work can continue;
- the choices have a known, bounded option set you can name;
- the user asked to be prompted with a menu, list, form, or dialog;
- a prior
questionnaireresult returnedQUESTIONNAIRE_NEEDS_CLARIFICATION.
Do not use questionnaire when:
- the question is genuinely open-ended and better answered in prose;
- one trivial confirmation is enough — just ask in normal text;
- you are requesting secrets, passwords, tokens, or other credentials;
- you already have the answer in context, or can determine it by reading files or running a read-only command.
Never invent a questionnaire to look thorough. Ask only what actually changes what you will do.
Question design rules
- Combine. Put every related question into one
startcall. Do not run several sequential questionnaires for one decision. - Stable IDs. Give each question and option a stable, descriptive, non-empty
id(deploy_target,target_staging). IDs are what you read back; labels are only display text. - Unique IDs. Question IDs must be unique in the call; option IDs must be unique within their question.
- Concise text. Short
label, one clearpromptsentence, and an optional shortdescriptionper option only when the label is not self-explanatory. - Honest types. Use
singlewhen exactly one answer is valid,multiwhen several are. Do not fake multi-select with several single questions. - Realistic bounds. A
multiquestion defaults tominSelections: 0; setminSelections: 1whenever an empty answer is not useful. SetmaxSelectionsonly when the task needs a ceiling. Selection bounds are rejected onsinglequestions. - Other.
allowOtherdefaults totrue. Set it tofalsewhen a custom answer is meaningless or unusable. - Bounded size. 1–20 questions, 1–50 options per question, IDs ≤128 chars, labels ≤200, prompts ≤2000, option descriptions ≤500.
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.
- 1mo ago First seen · 133 lines · 110 tokens per session scan A 797aa14ad280
questionnaire is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (91 stars, last pushed yesterday), licensed MIT. It adds 110 tokens to every session and 1,600 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
convex-component-authoring
How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management.
npm-docs
Use this skill whenever the user asks about npm, package management, publishing packages, semantic versioning, npm CLI commands, or Node.js dependencies. Covers npm 12.x including the registry, scopes, organizations, security (audit, provenance, 2FA), CI/CD integration, workspaces, scripts, .npmrc configuration, and…
convex-component-authoring
How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management.
dependency-manager
Manage project dependencies — update packages, audit vulnerabilities, resolve conflicts, and keep dependencies healthy. Use when updating packages, fixing vulnerability alerts, or resolving dependency issues.
colab-finetuning
Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…