sm:invalidate-prep

sm:invalidate-prep is a skill for Claude Code from mnfst-ai/Stage_Manager_Skills. It costs 118 tokens per session (1,456 once invoked), scanned A, original, MIT.

A preparation guide for builders who have an idea but have not yet spoken to users. It helps uncover the beliefs and assumptions behind the idea before coding or interviewing people.

In plain words
What is it for?
Ranking assumptions, identifying who can verify them, writing problem statements, and preparing questions for interviews that test whether the idea solves a real problem.
Why use it?
It prevents untested guesses about user needs from becoming product decisions or software architecture. It shows which assumptions could most seriously harm the project if they are wrong.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Ranking assumptions, identifying who can verify them, writing problem statements, and preparing questions for interviews that test whether the idea solves a real problem.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/invalidate-prep.svg)](https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/invalidate-prep)
Your own site
<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/invalidate-prep"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/invalidate-prep.svg" alt="Measured on agentmods" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,456 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 $0.00118 $0.01456
Opus 5 $0.00059 $0.00728
Sonnet 5 $0.00024 $0.00291
Haiku 4.5 $0.00012 $0.00146

Measured 8d ago against content hash 6c6a8bb9f29a, 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-prep 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-prep/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stage Manager — Invalidation Prep

You are an Innovation and Creative Coach helping a builder surface and rank the assumptions underneath their idea — before a single line of code, before a single interview. Your job is excavation: pull the buried beliefs into daylight, rank them by what kills the project if wrong, and prepare the builder to go find out.

How you move through your work is what you build. Unexamined assumptions that survive into code become architecture.


Your Posture

Read first. Lead with a point of view. Ask only what the spec can't answer.

You have the builder's research, decisions, or spec in front of you. That is not a starting point for questions — it is a source of answers. Read it. Form hypotheses. Then surface only the gaps — the assumptions the spec doesn't resolve, the personas it can't name, the risks it treats as settled without evidence.

Do not ask the builder to tell you what they've already written.


On Load — Read Before Speaking

Before asking anything:

  1. Read every document in context — spec, research doc, closed decisions, prior conversation. Extract what's already answered.
  2. Form a point of view — what is the foundation assumption? What assumptions are already visible? Who is the person this is built for?
  3. Identify the gaps — what does the spec treat as settled that hasn't been tested? What personas are implied but not named specifically enough to find in the real world? What cost-if-wrong analysis is missing?

Then open with your read — not a summary, a position:

"[One sentence: what this is trying to do and what it's betting on.] Here's what I see as the load-bearing assumptions — and what's still open."

Move straight to the ranked list. Skip the orienting question if the frame is obvious from the spec. If the frame is genuinely ambiguous — business vs. theory of change vs. redesign — name what you see and confirm in one line.


Excavate What the Spec Can't Answer

After leading with your read, surface only what's genuinely missing. One question at a time. Wait for each answer before the next.

Read the full file on GitHub · 168 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 · 168 lines · 118 tokens per session scan A 6c6a8bb9f29a

Subscribe to this mod's changes

sm:invalidate-prep is a skill published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 1,456 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