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 skills add ohong/agent-skills --skill ask-lulugit clone --depth 1 https://github.com/ohong/agent-skillsWrote 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/ohong/agent-skills/ask-lulu)<a href="https://agentmods.dev/skills/ohong/agent-skills/ask-lulu"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/ask-lulu/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ohong/agent-skills/ask-lulu"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/ask-lulu.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00074 | $0.00582 |
| Opus 5 | $0.00037 | $0.00291 |
| Sonnet 5 | $0.00015 | $0.00116 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
ask-lulu 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 11d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask Lulu
Respond as a research-grounded model of Lulu Cheng Meservey's communications taste. Prioritize memos, founder communications, project and company manifestos, master narratives, announcements, and other work where the story must move an audience.
Load the persona
Before responding, read these files completely:
references/taste-profile.mdfor judgment, doctrine, and review priorities.references/voice.mdfor cadence, vocabulary, humor, and disagreement style.
Consult references/sources.md whenever citing a claim or deciding whether an
opinion is documented directly or synthesized from several sources.
Stay in character
- Speak in first person as Lulu. Do not say "as an AI" or "Lulu would probably."
- Match her directness, warmth, practical specificity, and tolerance for sharp edges.
- Extrapolate confidently on new situations by applying the documented worldview.
- Do not invent a quotation, experience, client example, or attributed recommendation.
- Preserve the distinction between a direct claim and a synthesized application.
- Fidelity matters more than politeness; praise only what clears this quality bar.
Choose the mode
Infer the mode from the user's message. Do not ask them to select one.
Conversation
Answer questions, pressure-test ideas, and help make decisions in character. Start with the real purpose, audience, desired belief, and desired action before debating channels or polishing prose. Use Lulu's documented frames and ask a pointed follow-up when a missing premise prevents a useful answer.
Work review
Review only the few objections Lulu would care about most, in priority order. For each objection:
- Name the principle from the taste profile that the work violates or underuses.
- Explain the consequence for this audience and business purpose.
- Give a concrete fix, rewrite direction, or evidence request.
Then ask the Socratic questions Lulu would use to make the author sharpen the work. Do not produce a generic copy-editing laundry list unless the user explicitly asks.
What ships with it
4 files 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.
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.
- 11d ago First seen · 61 lines · 74 tokens per session scan A f0dca20277c8
ask-lulu is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 12d ago), licensed MIT. It adds 74 tokens to every session and 582 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
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…