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 ivklgn/ai-kit --skill ask-megit clone --depth 1 https://github.com/ivklgn/ai-kitWrote 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/ivklgn/ai-kit/ask-me)<a href="https://agentmods.dev/skills/ivklgn/ai-kit/ask-me"><img src="https://agentmods.dev/badge/skills/ivklgn/ai-kit/ask-me/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/ivklgn/ai-kit/ask-me"><img src="https://agentmods.dev/badge/skills/ivklgn/ai-kit/ask-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00142 | $0.01388 |
| Opus 5.5 | $0.00057 | $0.00555 |
| Sonnet 5.5 | $0.00028 | $0.00278 |
| Haiku 4.5 | $0.00014 | $0.00139 |
Grade A, and why
ask-me 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask Me
Produce a list the human can work through without re-reading the session — every line on it must be something only they can do.
Speed contract
Call no tools. Everything needed is in context: the goal, the plan, what was tried, what failed, what the user already said. Never Read, Grep, Glob, search, or launch a subagent to "check whether it's really needed" — if the session does not show the limit, the item does not exist yet.
Language
Write in the language the user has been writing in this session, not the language of this skill. Mixed input follows the dominant language of the user's own messages. Translate the kind tags and labels — tags in Russian: Решить / Ответить / Доступ / Принести / Сделать; item labels: Причина (why me not you) / Блокирует / По умолчанию / Ответ; closing line: Пока жду. Keep identifiers verbatim — paths, commands, hostnames, branch names, error text.
What qualifies
An item earns its place only when the session shows the agent genuinely cannot do it. Five kinds:
| Tag | The item is… | Typical sign in the session |
|---|---|---|
| Decide | a choice the user owns: product behaviour, scope, priority, spending, anything irreversible | two valid approaches, and picking one changes the work |
| Answer | a fact only the user has: intended behaviour, what production does, what a colleague agreed | the agent guessed, or asked and got no reply |
| Access | a credential, permission, VPN, MCP server that failed to connect, a tool call the user declined | an auth error, "server failed to connect", a denied permission |
| Fetch | data in a system the agent cannot reach: dashboard, email, chat thread, ticket, remote log, closed database | the plan needs a number or a file the session never contained |
| Do | an action in the world or in an interactive session: approve, merge, pass 2FA, run an interactive login, restart a box, look at a screen | the next step is a click, a signature, or ! <command> |
Not an item:
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.
- 1mo ago First seen · 78 lines · 142 tokens per session scan A e5b75d021345
ask-me is a skill published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 1,388 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.
agent-svelte-expert
Specialist subagent: Svelte 5 runes, SvelteKit routing, form actions, and compile-time reactivity specialist. Use when building Svelte or SvelteKit applications, implementing rune-based state management, or working with SvelteKit features. Trigger phrases: Svelte, SvelteKit, runes, $state, $derived, $effect, $props…
performance-engineering
Web Vitals, bundle optimization, CDN, caching, and load analysis. Use when diagnosing slow pages or APIs, reducing bundle size, or designing caching and performance budgets.