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/prabhdeepsingh/claude-plugins/intent-interviewnpx skills add PrabhdeepSingh/claude-plugins --skill intent-interviewgit clone --depth 1 https://github.com/PrabhdeepSingh/claude-pluginsWhat 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 | $0.00098 | $0.01338 |
| Opus 5 | $0.00049 | $0.00669 |
| Sonnet 5 | $0.00020 | $0.00268 |
| Haiku 4.5 | $0.00010 | $0.00134 |
Grade A, and why
intent-interview 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 3d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Interview — find out what they actually want before building anything
The most expensive misunderstanding is not a wrong implementation of the right thing — it's the right implementation of the wrong thing. A user who asks for "a dashboard for our metrics" may, two questions later, turn out to need a list. Different artifact, different scope, different work — and no amount of good speccing or good design recovers from interviewing zero. [[design-tree]]'s interview confirms the problem behind a design; this skill runs earlier and cheaper, for the case where the requested artifact itself is the hypothesis to test.
When to apply this
Interactively, when a request names an artifact but not the outcome ("build me X" with the why, the audience, or the success measure unstated), or when you notice you could not predict how the user would answer basic questions about it. Skip it when intent, constraints, and success criteria are already stated — restate them and proceed — and never run it in a non-interactive context (CI, a factory pass, a subagent, a scheduled run): nobody is there to answer, so an underspecified ask is written into the hand-off as a blocker instead.
How to apply this
1. Write a hypothesis, with a confidence number
Before asking anything, write (for yourself) what you believe they actually want and how confident you are. The honesty test for the number: can you predict the user's reactions to the next three questions you would ask? If not, the number is inflated. Below ~70%, name in one line what's missing — that gap is what the questions must close, and it keeps the interview aimed instead of ritual.
2. One question at a time, each with a guess attached
Ask exactly one question per message, and attach your current best guess to it ("Q: who reads this every day? My guess: the on-call engineer, during incidents"). Why one: the user can't react to hypotheses buried in a list, batches get skim-read, and the third question usually depends on the first answer. Why the guess: people correct a wrong guess faster than they compose an answer from nothing — and the guess commits you to being visibly wrong, which is the point. Occasionally guess in a direction you expect pushback on; a guess engineered to be agreed with tests nothing.
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.
- 3d ago First seen · 75 lines · 98 tokens per session scan A 224f975a17a1
intent-interview is a skill published in the GitHub repository PrabhdeepSingh/claude-plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 98 tokens to every session and 1,338 once invoked, about $0.0005 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
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
strategy-red-team
Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by impact × likelihood × cheapness-to-test, and returns the cheapest test and kill criteria for each. Use when stress-testing a plan, pressure-testing a strategy…
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
competitive-battlecard
Create sales-ready competitive battlecards comparing your product against a specific competitor — positioning, feature comparison, objection handling, and win/loss patterns. Use when preparing sales teams, creating competitive materials, or responding to 'why not competitor X?'.
create-business
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…