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/donald-ada/workinggenius/waitwhatnpx skills add donald-ada/workinggenius --skill waitwhatgit clone --depth 1 https://github.com/donald-ada/workinggeniusWrote 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/skills/donald-ada/workinggenius/waitwhat)<a href="https://agentmods.dev/skills/donald-ada/workinggenius/waitwhat"><img src="https://agentmods.dev/badge/skills/donald-ada/workinggenius/waitwhat.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00420 |
| Opus 5 | $0.00026 | $0.00210 |
| Sonnet 5 | $0.00010 | $0.00084 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
waitwhat 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 4d 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.
What it actually says
Wait, What?
The user typing this means one thing: your map of what they understood was wrong. An explanation is a checkpoint like any other, and this one failed — the repair is a corrected map, not a louder pitch. Not "be brief", either: an agent told to be brief writes telegrams; an agent told "you lost me" backs up and supplies the ground.
Re-pitch what you just said, for a reader who was not inside your head:
- Add the missing premises — the context that makes the conclusion parseable, which you had loaded and they didn't. Behavior level, not implementation level.
- Speak the project's language — terms from the project's glossary (
CONTEXT.md, where it keeps one), never codenames or shorthand this conversation invented. Leaning on a concept no shared vocabulary covers? Define it now — and if there's a glossary, write it in. - Shorter and clearer, not shorter and blunter. Deleting words isn't the job; supplying the ground is.
- End on evidence, not delivery. "Explained" is a claim, and its evidence is the reflection, not the speech: close with the one question whose answer shows whether the map is repaired. A wrong answer is a finding about the explanation, not the reader — repair again from where it broke.
A second /waitwhat on the same topic is a finding, not a coincidence: the gap isn't the wording, it's a missing shared concept. Name it, define it in the glossary, then explain with it — the repair loop feeds the project's memory, so the next first draft lands on its own.
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.
- 4d ago First seen · 20 lines · 52 tokens per session scan A e3b22a3e2871
waitwhat is a skill published in the GitHub repository donald-ada/workinggenius (5 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 420 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 2026-08-31.
Other skills, from other repositories
practice-cognition
触发：当你提出了方案、假设或判断，需要通过实践验证、试错迭代或复盘升级认知时调用；常见信号包括 experiment、prototype、validate、iterate、feedback loop。 English: Trigger when an idea, hypothesis, or plan must be tested in practice and improved through iteration. Use this skill to move from action to understanding and back to action in a spiral learning loop.
engineering-onboarding
Create an onboarding guide for an engineer joining a team that consumes the design system. Trigger when someone says: onboard new engineer, developer getting started guide, new engineer guide, engineering onboarding, first day for developers, frontend onboarding, or anything about helping an engineer new to the team…
async-learning-teacher
Transform saved links, papers, articles, posts, videos, and reference collections into approachable AI teaching artifacts for later study. Use when a user wants to queue learning material, create a readable explanation from a source, teach a paper or post step by step, or run an interactive tutor that validates…
learn
Must be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are saved for future turns.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.
teach-me
Teach the learner to deeply understand a body of work — the current session's changes, a PR, an ADR, or any topic they name — the problem and why it existed, the solution and why it was built that way, and why it matters, incrementally and confirming mastery at each stage before advancing. Use when the user wants to…