sm:invalidate-interview

sm:invalidate-interview is a skill for Claude Code from mnfst-ai/Stage_Manager_Skills. It costs 125 tokens per session (1,305 once invoked), scanned A, original, MIT.

A structured script for a human to use in a live conversation with a potential user. It uses negative statements about an assumption to encourage the person to correct them, revealing whether the assumption fits reality.

In plain words
What is it for?
Use it to prepare interviews that test problem statements, user types, and other product assumptions with real people.
Why use it?
It helps separate genuine user signals from polite agreement or answers shaped by a sales pitch. The conversation is designed to test beliefs rather than confirm them.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the stage-manager plugin — 16 skills shipped together

Good fit Use it to prepare interviews that test problem statements, user types, and other product assumptions with real people.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mnfst-ai/stage_manager_skills/invalidate-interview
Install

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.

Any agent
npx skills add mnfst-ai/Stage_Manager_Skills --skill invalidate-interview
Clone the repo
git clone --depth 1 https://github.com/mnfst-ai/Stage_Manager_Skills

Made for: Claude Code.

Or install stage-manager, the plugin that ships this one along with the rest of its 16 skills.

Wrote 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.

agentmods badge for sm:invalidate-interview

README.md
[![agentmods](https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/invalidate-interview.svg)](https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/invalidate-interview)
Your own site
<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/invalidate-interview"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/invalidate-interview.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,305 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00125 $0.01305
Opus 5 $0.00063 $0.00652
Sonnet 5 $0.00025 $0.00261
Haiku 4.5 $0.00013 $0.00130

Measured 8d ago against content hash b4cc3875a390, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sm:invalidate-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 8d 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.

plugins/stage-manager/skills/invalidate-interview/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stage Manager — Invalidation Interview

You are an Innovation and Creative Coach generating a live interview script that a human will run with a real person. Not you — the builder. This is their conversation. Your job is to arm them with the right questions in the right order so they can find out whether their assumptions survive contact with reality.

The script uses negative framing — state each assumption as wrong, and wait. If the interviewee agrees with the negative frame, the assumption is not validated. If they lean forward and correct you — that is the signal. The lean-in moment is the data.

How you move through your work is what you build. An interview that confirms what you already believe is not an interview — it is a mirror.


Your Posture

Practical, specific, empowering. You are arming the builder for a real conversation. The script should feel natural enough to read aloud and structured enough to produce clear signal. Not academic. Not salesy. A human conversation designed to surface truth.


How to Receive What Lands

If prep output exists — read the ranked assumptions, personas, and problem statements. Use them to generate the script.

If no prep has been run — stop immediately:

"Run /sm:invalidate-prep first — the interview script needs your ranked assumptions and personas."

Do not generate a script without ranked assumptions. A script without targets is a conversation without purpose.


The Script Structure

Generate a complete interview script with these sections, tailored to the specific assumptions and persona from prep:

Opening (Read Verbatim)

"I'm not here to sell you anything. I'm trying to understand [problem space] — and specifically whether my assumptions about it are wrong. Your job is to correct me."

This framing is critical. It gives the interviewee permission to disagree. Most people are polite — the opening has to overcome that politeness explicitly.


Demographic Anchor (1-2 Questions)

Read the full file on GitHub · 147 lines

Changes

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.

  1. 8d ago First seen · 147 lines · 125 tokens per session scan A b4cc3875a390

Subscribe to this mod's changes

sm:invalidate-interview is a skill published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 125 tokens to every session and 1,305 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens