vibe-research

vibe-research is a skill for Claude Code from KhazP/vibe-coding-prompt-template. It costs 49 tokens per session (1,840 once invoked), scanned A, original, MIT.

A guided research process for checking whether an app idea is worth building. It asks structured questions and records findings for the next planning stage.

In plain words
What is it for?
Use it to research a new app idea, assess its market fit, and create a handoff document for writing product requirements.
Why use it?
It helps uncover the target users, platform, budget, timeline, and role of AI before coding begins. This reduces the chance of building from unclear assumptions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code; installed under .agents/ (shared by several agents).

Good fit Use it to research a new app idea, assess its market fit, and create a handoff document for writing product requirements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/khazp/vibe-coding-prompt-template/vibe-research
About the project

KhazP/vibe-coding-prompt-template is a collection of templates and workflows that use large language models to turn an idea into a product requirements document, technical design, and minimum viable product plan. It is for people building MVPs with AI coding agents or chat tools, and its catalogue entries support that planning and coding workflow.

KhazP/vibe-coding-prompt-template · 3,053 stars · on GitHub · vibeworkflow.app

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 KhazP/vibe-coding-prompt-template --skill vibe-research
Clone the repo
git clone --depth 1 https://github.com/KhazP/vibe-coding-prompt-template

Made for: Claude Code.

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 vibe-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/khazp/vibe-coding-prompt-template/vibe-research/github.svg)](https://agentmods.dev/skills/khazp/vibe-coding-prompt-template/vibe-research)
Your own site
<a href="https://agentmods.dev/skills/khazp/vibe-coding-prompt-template/vibe-research"><img src="https://agentmods.dev/badge/skills/khazp/vibe-coding-prompt-template/vibe-research/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 vibe-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/khazp/vibe-coding-prompt-template/vibe-research"><img src="https://agentmods.dev/badge/skills/khazp/vibe-coding-prompt-template/vibe-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,840 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 159
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00049 $0.01840
Opus 5 $0.00024 $0.00920
Sonnet 5 $0.00010 $0.00368
Haiku 4.5 $0.00005 $0.00184

Measured 10d ago against content hash 3de60d88db71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vibe-research 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 10d 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.

.agents/skills/vibe-research/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vibe-Coding Deep Research

You are helping the user validate and research their app idea. This is Step 1 of the vibe-coding workflow.

Your Role

Guide the user through a structured research process to validate their idea before building. Ask questions one at a time and wait for responses.

Handoff Context (required output)

End the research document with this block so the PRD step can pre-fill instead of re-asking:

## Handoff Context
<!-- Machine-readable summary for the next workflow step. Do not delete; the next prompt in the workflow reads this block. -->
- Stage: research
- App name: [app name]
- User level: [A | B | C]
- Target platform: [web / mobile / desktop]
- Budget: [budget]
- Timeline: [timeline]
- AI in product scope: [yes / no / undecided]
- Source files: research-[AppName].md

Interview Rules

  • Use your native question tool (e.g. AskUserQuestion in Claude Code) to ask questions when available; otherwise ask in plain chat.
  • Ask one question at a time by default: ask, wait for the answer, then continue.
  • If the user answers several questions at once, accept those answers, skip the questions they covered, and carry on with the ones still open. Never re-ask something they already told you.
  • If the user says "I don't know" or seems unsure, propose a sensible default and ask them to confirm it rather than leaving the answer blank.
  • Never invent an answer they did not give. If a reply is vague, ask one short follow-up.
  • Cover every question in the lists below — but let the user's own answers, and anything a ## Handoff Context block already supplies, close them out.

Session Continuity

  1. Encourage users to keep research, PRD, and tech design in one linked conversation.
  2. If context grows too large, summarize/compact instead of starting an empty thread.
  3. If restarting is unavoidable, create a continuity handoff summary: project, users, features, constraints, open questions.

Naming Policy

Use model family names in recommendations unless the user requests pinned versions. Verify pricing, quotas, model names, and beta features against official sources before writing them as facts.

Read the full file on GitHub · 160 lines

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. 10d ago First seen · 160 lines · 49 tokens per session scan A 3de60d88db71

Subscribe to this mod's changes

vibe-research is a skill published in the GitHub repository KhazP/vibe-coding-prompt-template (3,053 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 1,840 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

vibe-coding-guardian

Behavioral modifier for AI coding assistants working with non-developers. Adapts AI behavior by risk level — fast for small changes, cautious for risky ones. Prevents debug death spirals, translates errors to plain language, auto-checkpoints with git, and runs periodic health checks. Always active, zero manual trigger…

kanyun-inc/reskill · 73 tokens

moai-workflow-thinking

Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.

modu-ai/moai-adk · 43 tokens

code-mate-antigravity

Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.

CherryHQ/cherry-studio · 43 tokens

code-mate-openclaw

Runs a local OpenClaw agent non-interactively and returns its structured response. Use when the user asks to delegate a bounded task to the OpenClaw main agent.

CherryHQ/cherry-studio · 41 tokens

code-mate-qoder

Runs the Code Mate Qoder CN CLI non-interactively with structured output. Use when the user asks to delegate a bounded coding task to Qoder.

CherryHQ/cherry-studio · 36 tokens

office-hours

YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to…

GCWing/BitFun · 168 tokens