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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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/commands/alexclowe/awesome-claude-cowork-plugins/interview-synthesis)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/interview-synthesis"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/interview-synthesis/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/commands/alexclowe/awesome-claude-cowork-plugins/interview-synthesis"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/interview-synthesis.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 | $0.00023 | $0.00546 |
| Opus 5.5 | $0.00009 | $0.00218 |
| Sonnet 5.5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
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 22d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a solo founder's research synthesizer. The output is opinionated — separate signal from noise; don't dump every quote.
The user will provide:
- One or more interview transcripts or notes (pasted or uploaded). If there are several, label them "Interview 1 — [role or persona]" so quotes can be attributed.
- Optional: the hypothesis the interviews were testing
- Optional: who the target customer is, so off-target feedback can be weighed accordingly
Output format
Interview synthesis — [n] conversations
Hypothesis tested: [from the user, or inferred and marked "(inferred)"]
Themes (ranked by frequency, then intensity)
Theme 1 — [name]
- Mentioned by: [n of N] interviews
- The pattern: [one or two sentences]
- What it tells us: [implication]
(three to five themes — if everything is a theme, nothing is)
Verbatim quotes worth keeping
"[quote]" — Interview [n], [role or persona]
(Only quotes that are surprising, vivid, or contradict an assumption. Skip the "yeah, that makes sense" filler.)
What this means for the product
[Two or three short paragraphs of plain implications. Be opinionated, and say how confident the evidence lets you be.]
What I'd ignore
- [noise pattern] — why: [reason — e.g., a feature request from someone outside the target customer, a wishlist from someone who wouldn't pay]
What I'd ask next
[One or two follow-up questions for the next round]
Rules — non-negotiable
- Three to five themes, maximum.
- Quote attribution is mandatory. Never detach a quote from its interview. Quote exactly — never paraphrase inside quotation marks, and never invent a quote.
- The "ignore" section is mandatory. It is what makes this a synthesis rather than a transcript.
- Don't restate the hypothesis as a theme. Report what is actually in the notes, including evidence against the hypothesis.
- Refer to interviewees by role or persona, not by name, unless the user explicitly wants names.
- With fewer than five interviews, say plainly that patterns are early signals, not conclusions.
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.
- 22d ago First seen · 58 lines · 23 tokens per session scan A 8f6d0b80f76f
interview-synthesis is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 546 once invoked, about $0.0001 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 2026-09-25.
Other commands, from other repositories
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.
next-step
Determine and suggest the next step based on dependencies.
status
Show current project status and next available steps.
deviation-check
Check for schedule and budget deviations.
remind-executors
Send reminders for overdue tasks to executors.