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 Waddling-Penguin/mogkit --skill prd-interrogategit clone --depth 1 https://github.com/Waddling-Penguin/mogkitWrote 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/waddling-penguin/mogkit/prd-interrogate)<a href="https://agentmods.dev/skills/waddling-penguin/mogkit/prd-interrogate"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/prd-interrogate.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 | $0.00003 | $0.01254 |
| Opus 5 | $0.00002 | $0.00627 |
| Sonnet 5 | $0.00001 | $0.00251 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
prd-interrogate 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 7d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
The PM is about to write a PRD. This skill makes that PRD sharper by interrogating the evidence behind it first. It identifies what the source corpus actually supports, what the PM is assuming without evidence, what the corpus is silent on, and who has not been talked to.
It does NOT write the PRD. The PM writes the PRD. Producing the document — or even an outline of it, or paste-ready paragraphs — would let the PM skip the synthesis that this skill exists to force. The output is a scaffold the PM thinks against, not a draft they edit. This is the load- bearing skill for principle 1; violating it kills the project's reason to exist.
Procedure
- Read
graph/graph.json. If it does not exist, tell the PM to rungraphifyfirst and stop. - Read
meta.health. Cold-start branch: ifhealth === "thin", state this prominently at the top of the response. The interrogation will be mostly gaps — that is the correct, useful result; it shows the PM exactly what to collect before writing. - Take the PM's stated PRD intent — the feature or problem the PRD will cover. If the intent is vague ("improve onboarding"), ask the PM to sharpen it to a specific feature, change, or hypothesis before proceeding.
- From the graph, gather every node and edge relevant to the intent. For each, note the provenance count and source-type spread.
- Separate the relevant material into four buckets:
a. Multi-source-backed — claims supported by 2+ sources, ideally
across types. These are the parts of the PRD the PM can write with
confidence.
b. Single-source — claims with one source of provenance. These
are the parts the PM should hedge or validate before committing.
c. Assumption —
Assumptionnodes in the graph the PRD would rely on. Empty provenance is the point. d. Silent — elements of the PRD intent the graph says nothing about at all. The PM would be flying blind here. - Identify which user segments and personas relevant to the intent are
thin or absent in
sources/. For each, write one specific question that segment alone could answer. - Emit the output contract below. Do not emit a PRD, a PRD outline, draft headings for a PRD, or prose that could be pasted into a 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.
- 7d ago First seen · 110 lines · 3 tokens per session scan A 94dba811b42c
prd-interrogate is a skill published in the GitHub repository Waddling-Penguin/mogkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 3 tokens to every session and 1,254 once invoked, about $0.0000 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 2026-08-31.
Other skills, from other repositories
find-skills
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.