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 ragnar-pwninskjold/tech-snacks --skill lite-prdgit clone --depth 1 https://github.com/ragnar-pwninskjold/tech-snacksWrote 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/ragnar-pwninskjold/tech-snacks/lite-prd)<a href="https://agentmods.dev/skills/ragnar-pwninskjold/tech-snacks/lite-prd"><img src="https://agentmods.dev/badge/skills/ragnar-pwninskjold/tech-snacks/lite-prd/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/ragnar-pwninskjold/tech-snacks/lite-prd"><img src="https://agentmods.dev/badge/skills/ragnar-pwninskjold/tech-snacks/lite-prd.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 | $0.00086 | $0.00808 |
| Opus 5 | $0.00043 | $0.00404 |
| Sonnet 5 | $0.00017 | $0.00162 |
| Haiku 4.5 | $0.00009 | $0.00081 |
Grade A, and why
lite-prd 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 11d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lite-prd
Turn a vague feature ask into a lightweight PRD by interviewing the user with AskUserQuestion, traversing the design tree (branch deeper when an answer opens new territory), persisting every round, and writing lite-prd.md.
What this does
- Reads the vague ask and picks a slug + output folder.
- Interviews the user in adaptive batches via
AskUserQuestion(2–4 grouped questions per round), up to ~50 questions total. - Traverses the design tree — when an answer materially changes scope or leaves a real ambiguity, branch deeper into that thread before moving on.
- Persists every question and answer to a Q&A log in the repo as it goes.
- Synthesizes the answers into
lite-prd.mdin the pasted format (minus Monetization).
Flags
--deep: exhaustive branching — pursue every plausible sub-thread until the tree is dry or the ~50-question budget is spent. Default (no flag) is model-judged, biased to fewer: only branch when an answer materially changes scope or leaves a real ambiguity, and prefer finishing over exhausting the budget.
Step 1 — Set up the workspace
- Derive a short kebab-case
<slug>from the feature ask (e.g. "team invites" →team-invites). - Create the folder
docs/lite-prd/<slug>/in the repo the skill was invoked in. If it already exists, reuse it and continue an in-progress run rather than clobbering. - Create/open the Q&A log at
docs/lite-prd/<slug>/qa-log.md. Seed it with the raw ask.
Step 2 — Interview by traversing the design tree
Read references/traversal-protocol.md and follow it exactly. It defines: how to seed the root questions, how to batch with AskUserQuestion, when to branch deeper vs. move on (and how --deep changes that), the ~50-question budget, and the persistence rule (write each round to qa-log.md immediately after the user answers, before asking the next batch).
Every round: ask → read answers → append the round to qa-log.md → decide whether to branch or advance.
Step 3 — Synthesize the PRD
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.
- 11d ago First seen · 51 lines · 86 tokens per session scan A ddeac7c4f923
lite-prd is a skill published in the GitHub repository ragnar-pwninskjold/tech-snacks (132 stars, last pushed 23d ago), licensed MIT. It adds 86 tokens to every session and 808 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…