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 flavien-ia/hypervibe-harness --skill add-aigit clone --depth 1 https://github.com/flavien-ia/hypervibe-harnessWrote 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/flavien-ia/hypervibe-harness/add-ai)<a href="https://agentmods.dev/skills/flavien-ia/hypervibe-harness/add-ai"><img src="https://agentmods.dev/badge/skills/flavien-ia/hypervibe-harness/add-ai/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/flavien-ia/hypervibe-harness/add-ai"><img src="https://agentmods.dev/badge/skills/flavien-ia/hypervibe-harness/add-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.01818 |
| Opus 5 | $0.00023 | $0.00909 |
| Sonnet 5 | $0.00009 | $0.00364 |
| Haiku 4.5 | $0.00005 | $0.00182 |
Grade A, and why
add-ai 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add AI - Intelligence inside the product
Adds AI to the user's application: a chat assistant, a processing step, a
generator. Everything routes through one file in the project
(src/server/ai.ts), and through OpenRouter, so that changing model is a
string to edit rather than a migration.
You own the feature: what it does, where it plugs in, what the user sees.
The brick underneath (the key, the budget, the shared file) is installed by
_ensure-ai, which every intelligence-needing skill of the plugin calls.
That is what guarantees the same three boundaries everywhere.
Communication
- Detect the user's language from the conversation (the user's own messages, anywhere in the session - not just this invocation: a bare slash command like
/bootstrapcarries no language signal by itself). If nothing in the conversation gives a signal, fall back to the OS locale (node -e "console.log(Intl.DateTimeFormat().resolvedOptions().locale)") before defaulting to English. ALWAYS reply in that language for every user-facing message: questions, progress, confirmations, summaries, errors - including any example text quoted in this skill, which is illustrative and must be translated, never sent verbatim. - Use plain, non-technical business language. Never expose internal script names (*.mjs) or jargon; describe actions in human terms.
- When generating user-facing content for the scaffolded project (UI labels, emails, copy), write it in the user's language too.
- Show progress as a short natural-language checklist (in-progress and done states).
What this skill refuses to do
Three boundaries, and they matter more than the features. They are applied by
_ensure-ai, so they hold identically whichever skill installed the AI:
- No code before a validated budget. The user sees what it will cost, in their currency, for their volume, from the live price catalogue. They say yes to a number.
- No key without a cap. The key created for the project carries a spending limit held by OpenRouter itself. A runaway loop hits a wall on the provider's side, not on a counter we wrote.
- No free model on personal data. Free models exist and are genuinely useful, but some providers train on what passes through. Free is for prototyping; production data goes to paid models with training refused.
What ships with it
2 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 · 140 lines · 45 tokens per session scan A 51c9c194bb16
add-ai is a skill published in the GitHub repository flavien-ia/hypervibe-harness (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 1,818 once invoked, about $0.0002 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.
Other skills, from other repositories
claude-api-in-prototypes
Call Claude from your HTML artifacts via window.claude.complete.
core
Core package for defining schemas, catalogs, and AI prompt generation for json-render. Use when working with @json-render/core, defining schemas, creating catalogs, or building JSON specs for UI/video generation.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
playwright
Playwright E2E testing patterns. Trigger: When writing Playwright E2E tests (Page Object Model, selectors, MCP exploration workflow). For Prowler-specific UI conventions under ui/tests, also use prowler-test-ui.
thinking-orbs
Add accessible animated AI loading and agent-status indicators with the React thinking-orbs library. Use when a chat, copilot, voice, search, generation, or tool-running interface needs a semantic working, searching, solving, listening, composing, or shaping state; when replacing a generic spinner with an AI activity…
globe-gl
Use when implementing globe.gl (Globe.GL) for 3D globe data visualization with WebGL/ThreeJS, including setup, data layers (points, arcs, polygons, labels), and integration patterns in plain HTML or React.