wait-what

wait-what is a skill for Claude Code, Codex from aethrox/doctrine. It costs 59 tokens per session (821 once invoked), scanned A, original, MIT.

A response guide for recognizing when an explanation confused someone and presenting the idea again in clearer, more relevant words.

In plain words
What is it for?
Re-explaining technical answers after follow-up questions, silence, or a direct signal such as “wait, what?”.
Why use it?
Repeating the same explanation usually does not fix a misunderstanding. This helps an agent change its explanation when the reader signals confusion.

Skill for Claude CodeCodex

Part of the doctrine plugin — 33 skills shipped together

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.

agentmods
npx agentmods add skills/aethrox/doctrine/wait-what
Any agent
npx skills add aethrox/doctrine --skill wait-what
Clone the repo
git clone --depth 1 https://github.com/aethrox/doctrine

Made for: Claude Code, Codex.

Or install doctrine, the plugin that ships this one along with the rest of its 33 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 wait-what

README.md
[![agentmods](https://agentmods.dev/badge/skills/aethrox/doctrine/wait-what.svg)](https://agentmods.dev/skills/aethrox/doctrine/wait-what)
Your own site
<a href="https://agentmods.dev/skills/aethrox/doctrine/wait-what"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/wait-what.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 821 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.00821
Opus 5 $0.00030 $0.00411
Sonnet 5 $0.00012 $0.00164
Haiku 4.5 $0.00006 $0.00082

Measured 5d ago against content hash 83400c268ccf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wait-what 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.

skills/wait-what/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wait, What?

Confusion after an explanation is a signal about the explanation, not the reader; repeating the same words louder fixes nothing. This skill's defining constraint, from ISO 24495-1 (the international plain-language standard)'s four governing principles: a re-pitch must be relevant (only what this reader needs right now, not everything that's true), findable (the point stated up front, not buried under setup), understandable (plain words, one idea per sentence), and actionable (the reader knows what to do or believe next): all four, not just "simpler words."

This is the recovery move for one specific moment: an explanation was just given and didn't land. For explaining something plainly from the start, or maintaining a running glossary for a non-technical audience, that's a broader concern this skill doesn't own.

Phase 1: Recognize the signal

The trigger is a response that shows the prior explanation didn't transfer: a follow-up question that reveals a different (wrong) mental model, silence where engagement was expected, or a direct signal like "wait, what?" Don't wait for an explicit "I don't understand"; a follow-up question aimed at the wrong layer of the problem is the same signal, just quieter.

Phase 2: Re-pitch, don't repeat

The failed explanation's words, structure, and level of detail didn't work; reusing them with more emphasis repeats the failure. Reframe from a different angle: a different analogy, a different starting point, or a different granularity (too abstract → concrete example; too detailed → the one-sentence version first).

Phase 3: Apply all four ISO 24495-1 principles

  • Relevant: cut everything the reader doesn't need to resolve their actual confusion right now. A re-pitch that repeats context they already have is why the first attempt was missed.
  • Findable: lead with the point itself, not the reasoning that arrives at it. A reader who's already confused won't survive a long windup before the answer appears.
  • Understandable: plain words over jargon, short sentences, one idea per sentence. If a technical term is unavoidable, define it inline rather than assuming it survived from the first attempt.
  • Actionable: end with what the reader should now do, believe, or decide. An explanation that's merely accurate but doesn't resolve into a next step leaves the reader exactly as stuck as before.
  • Punctuation: write the re-pitch without em dashes, using a comma, colon, period, or a reworded sentence instead.

Read the full file on GitHub · 42 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 42 lines · 59 tokens per session scan A 83400c268ccf

Subscribe to this mod's changes

wait-what is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 24d ago), licensed MIT. It adds 59 tokens to every session and 821 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

openspec-verify-change

Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

Fission-AI/OpenSpec · 32 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

planning-and-task-breakdown

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

shashankswe2020-ux/whoop-mcp · 56 tokens

qa-knowledge

To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.

griddynamics/rosetta · 32 tokens