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 interview-guidegit 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/interview-guide)<a href="https://agentmods.dev/skills/waddling-penguin/mogkit/interview-guide"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/interview-guide/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/waddling-penguin/mogkit/interview-guide"><img src="https://agentmods.dev/badge/skills/waddling-penguin/mogkit/interview-guide.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01379 |
| Opus 5.5 | $0.00001 | $0.00552 |
| Sonnet 5.5 | $0.00001 | $0.00276 |
| Haiku 4.5 | $0.00000 | $0.00138 |
Grade A, and why
interview-guide 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
A discovery interview is most valuable when the interviewer walks in knowing what the graph currently doesn't know. This skill reads the graph and produces a guide pointed at the gaps that would change the most if filled — not a generic discovery questionnaire that any PM could have written.
Each question is tied to a named gap in the graph, so the PM understands why it's on the list. The questions follow interview-craft rules: they ask about past behaviour, not hypothetical futures; they are open-ended and non-leading; they avoid pitching the product.
It does NOT script a sales conversation, prepare answers, or anticipate what the interviewee "should" say. The interviewer enters open; the guide just makes sure they enter pointed at the right gaps.
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 that on a thin corpus the gaps are everywhere — the guide should focus on the highest-leverage first gap (usually: which segment has the most weight on the team's current direction?). One well-targeted interview against a thin corpus is more valuable than a long guide chasing every gap. - Identify the load-bearing gaps in the graph. Sources of gaps:
a. Segments named in the corpus but represented by ≤1 source.
b.
Assumptionnodes adjacent to a major decision (i.e. the PRD intent doc or memo references them). c. Pains or Needs supported by only one source — single-source pains pointing at scope are high-leverage to triangulate. d.contradictsedges — the graph itself records that two sources disagree; resolving the contradiction often unlocks the decision. - If the PM has named a specific segment or persona to interview, filter the gaps to those that segment alone can fill. If not, pick the top 3 load-bearing gaps in the graph regardless of segment.
- For each chosen gap, write 1–3 interview questions. Rules:
- Behavioural, not hypothetical. Ask about what happened, not what would you do if. Bad: "Would you use feature X?" Good: "Walk me through the last time you tried to do X — what did you actually do?"
- Open, not leading. Bad: "Don't you find the import frustrating?" Good: "Tell me about importing your previous data — what was the experience like?"
- JTBD-anchored. Frame around the user's job, not the product. "When you were trying to set up the team, what did you need to figure out?" over "What do you think of our onboarding?"
- One question at a time. No compound questions.
- Add a short warm-up section (2–3 questions to set context and relax the interviewee) and a short close section (a single "is there anything I didn't ask that I should have?" closer).
- Emit the output contract.
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 · 126 lines · 3 tokens per session scan A c859b71cbee1
interview-guide is a skill published in the GitHub repository Waddling-Penguin/mogkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 3 tokens to every session and 1,379 once invoked, about $0.0000 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 2026-08-31.
Other skills, from other repositories
janitor-discover
Find new skills on GitHub or check a specific skill before installing. Use when the user wants to search for skills, evaluate a skill URL, check overlap and security risk before installing, or compare a local skill against alternatives. Trigger with '/janitor-discover'.
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.
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.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.