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/adamfaik/claude-code-pm-starter/interview-synthesisnpx skills add adamfaik/claude-code-pm-starter --skill interview-synthesisgit clone --depth 1 https://github.com/adamfaik/claude-code-pm-starterWrote 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/adamfaik/claude-code-pm-starter/interview-synthesis)<a href="https://agentmods.dev/skills/adamfaik/claude-code-pm-starter/interview-synthesis"><img src="https://agentmods.dev/badge/skills/adamfaik/claude-code-pm-starter/interview-synthesis.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 | $0.00044 | $0.00427 |
| Opus 5 | $0.00022 | $0.00214 |
| Sonnet 5 | $0.00009 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
interview-synthesis 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 5d 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
Interview synthesis
Turn what a user said into something the team can act on, and file it where future sessions will find it.
Steps
- Take the raw material. A transcript, rough notes, or a voice-note dump. Ask for the interview goal and who the participant was (role, segment) if not stated.
- Separate observation from interpretation. First pass: what the participant actually said and did, with short verbatim quotes. Second pass: what you and the user think it means. Never blend the two; a quote is evidence, a reading is a hypothesis.
- Structure the synthesis:
- Participant: role, segment, context, date.
- Goal of the session.
- What they said and did: the strongest verbatim moments, each with a one-line setup.
- Readings: the hypotheses these moments support or weaken, stated as hypotheses.
- Contradictions: where what they said conflicts with what they do, or with previous interviews.
- Follow-ups: what to probe in the next session.
- File it. Save to
operations/with the date and participant slug in the filename, for example2026-08-14-interview-nadia-churn.md. - Promote what's durable. If a finding holds across several interviews, offer to update
context/users.md(What we know) with a one-line digest pointing at the filed syntheses. Single-interview findings stay inoperations/; patterns get promoted.
Rules
- Quotes stay verbatim, including hesitations that carry meaning. Cleaning up a quote destroys the evidence.
- Flag leading questions you notice in the transcript; the next interview gets better.
- Never present one participant's view as "users want". One voice is a data point.
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.
- 5d ago First seen · 29 lines · 44 tokens per session scan A 03b8c00819c0
interview-synthesis is a skill published in the GitHub repository adamfaik/claude-code-pm-starter (10 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 427 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…