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.
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.
git clone --depth 1 https://github.com/KhazP/vibe-coding-prompt-templateWrote 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/commands/khazp/vibe-coding-prompt-template/vibe-research)<a href="https://agentmods.dev/commands/khazp/vibe-coding-prompt-template/vibe-research"><img src="https://agentmods.dev/badge/commands/khazp/vibe-coding-prompt-template/vibe-research.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00176 |
| Opus 5 | $0.00000 | $0.00088 |
| Sonnet 5 | $0.00000 | $0.00035 |
| Haiku 4.5 | $0.00000 | $0.00018 |
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 9d 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.
What it actually says
/vibe-research — Step 1: Deep research
Step 1 of the vibe-coding workflow: validate the app idea with deep research before anything gets built.
Read part1-deepresearch.md at the repository root and follow it as the single source of truth. (If it isn't in this project, ask the user to paste it.)
The essentials:
- Ask questions ONE at a time and wait for each answer — never dump the whole question bank at once.
- Echo back a short verification summary of your understanding before writing anything.
- Write the output to
docs/research-[AppName].md. - End the doc with the
## Handoff Contextblock defined in part1 — Part 2 reads it to skip re-asking questions.
Done? Point the user to the next stage: /vibe-prd.
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.
- 9d ago First seen · 14 lines · 0 tokens per session scan A 61e222ac27ee
vibe-research is a command published in the GitHub repository KhazP/vibe-coding-prompt-template (3,050 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 176 tokens. 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 commands, from other repositories
prd
You're helping the user create a Product Requirements Document — the most important document before building. This defines WHAT to build, WHO it's for, and WHY it matters.
implement
You're helping the user build. Time to write code.
checklist
You're helping the user break down their project into an ordered, actionable checklist.
plan
You're helping the user plan a software project or feature.
test
Let's validate that what was built actually works.
fix
Something's broken. Let's diagnose and fix it.