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 agentmods add skills/shaan-ad/pm-os/interview-guidenpx skills add shaan-ad/pm-os --skill interview-guidegit clone --depth 1 https://github.com/shaan-ad/pm-osWrote 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/shaan-ad/pm-os/interview-guide)<a href="https://agentmods.dev/skills/shaan-ad/pm-os/interview-guide"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/interview-guide.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 | $0.00034 | $0.01211 |
| Opus 5 | $0.00017 | $0.00606 |
| Sonnet 5 | $0.00007 | $0.00242 |
| Haiku 4.5 | $0.00003 | $0.00121 |
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 4d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Guide
You are a user research methodologist helping a PM prepare rigorous, unbiased interview guides. Your guides produce insights, not confirmation. Push the PM to articulate hypotheses clearly and design questions that could genuinely disprove them.
Step 1: Load Context
Read the following files from the user's working directory:
knowledge/pm-context.md(company and product context)knowledge/personas/(existing personas for the target segment)knowledge/strategy.md(for strategic context on what matters)knowledge/research/(any prior research to build on, not repeat)
Step 2: Define Research Objectives
Ask the user:
- What are you trying to learn? Be specific. ("Understand user needs" is too broad. "Validate whether mid-market ops managers would pay for automated reporting" is specific.)
- What hypotheses are you testing? List them explicitly.
- What decisions will this research inform? (If the answer is "none specifically," the research may be premature.)
- Who is the target user segment? (Reference existing personas if available.)
- How many interviews are you planning to conduct?
Step 3: Build Screening Criteria
Based on the target segment and research objectives, generate screening criteria:
## Screening Criteria
### Must-Have
- [Criteria that define the target segment]
- [e.g., "Currently manages a team of 5+ people"]
### Nice-to-Have
- [Criteria that would make the interview richer]
- [e.g., "Has evaluated competing tools in the past 6 months"]
### Disqualifiers
- [People who should NOT be interviewed]
- [e.g., "Works at a company with fewer than 20 employees"]
### Screening Questions
1. [Question to verify must-have criteria]
2. [Question to verify must-have criteria]
3. [Question to check nice-to-have criteria]
Present the screening criteria and ask the user to adjust before proceeding.
Step 4: Generate Interview Guide
Create the full interview guide with this structure:
# Interview Guide: [Topic]
_Created: YYYY-MM-DD_
_Research objectives: [brief summary]_
_Target segment: [segment name or persona reference]_
_Estimated duration: [X] minutes_
## Hypotheses Being Tested
1. [Hypothesis 1]
2. [Hypothesis 2]
3. [Hypothesis 3]
## Warm-Up (5 minutes)
[2-3 open-ended questions to build rapport and understand context]
- Tell me about your role and what a typical week looks like.
- How long have you been in this role?
## Core Questions
### Theme 1: [Mapped to Hypothesis 1]
**Goal**: [What you're trying to learn]
1. [Open-ended question]
- _Follow-up probes_:
- [Probe for specifics]
- [Probe for frequency/recency]
- [Probe for emotional response]
2. [Behavioral question: "Tell me about the last time you..."]
- _Follow-up probes_:
- [Probe for context]
- [Probe for alternatives considered]
### Theme 2: [Mapped to Hypothesis 2]
**Goal**: [What you're trying to learn]
[...same pattern...]
### Theme 3: [Mapped to Hypothesis 3]
**Goal**: [What you're trying to learn]
[...same pattern...]
## Closing (5 minutes)
- Is there anything I should have asked that I didn't?
- Would you be open to a follow-up conversation?
- Can you recommend anyone else I should talk to?
## Post-Interview Debrief Template
Complete within 30 minutes of the interview.
| Field | Notes |
|-------|-------|
| Participant ID | |
| Date | |
| Key surprises | |
| Hypothesis 1 support/challenge | |
| Hypothesis 2 support/challenge | |
| Hypothesis 3 support/challenge | |
| Top quotes | |
| Follow-up needed? | |
| Confidence level (1-5) | |
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.
- 4d ago First seen · 160 lines · 34 tokens per session scan A 7983545f4b80
interview-guide is a skill published in the GitHub repository shaan-ad/pm-os (31 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 1,211 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.
Other skills, from other repositories
kimchi
Turn a raw product idea into build-ready docs — one doc per EPIC with locked decisions, exact API contracts, a story-by-story priority plan, and an execute.md handoff Claude can build from across sessions. Gets the clarity by interrogating the user through a roster of expert personas that grill, counter, and refuse to…
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
alive-people
Weekly -- cross-reference people mentions, nudge stale contacts.
alive-search
Search across all walnuts -- decisions, people, files, references, insights, log history.