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 _ensure-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/_ensure-ai)<a href="https://agentmods.dev/skills/flavien-ia/hypervibe-harness/_ensure-ai"><img src="https://agentmods.dev/badge/skills/flavien-ia/hypervibe-harness/_ensure-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/_ensure-ai"><img src="https://agentmods.dev/badge/skills/flavien-ia/hypervibe-harness/_ensure-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Privilege Escalation · line 87 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Anti-Refusal · line 316 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00053 | $0.04330 |
| Opus 5 | $0.00026 | $0.02165 |
| Sonnet 5 | $0.00011 | $0.00866 |
| Haiku 4.5 | $0.00005 | $0.00433 |
Grade B, and why
_ensure-ai scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
model call following the project's own pattern. Do not lecture, do not add a How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ensure AI - The single brick, and its three guardrails
You guarantee that the project can call a model through one file and one key, and that the three guardrails hold. Every skill that needs intelligence calls you first, so that no skill ever opens its own route to a provider.
You are silent when there is nothing to do. A project that already has its brick gets no dialogue: you add the usage entry and hand back.
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).
The three guardrails, and where each one lives
They are not of the same nature, which is why they cannot all live in a script:
| Guardrail | Nature | Where it is applied |
|---|---|---|
| A budget the user validated | A conversation | Step 3 of this skill: an estimate from the live catalogue, and the user says yes to a number |
| A key the provider itself caps | Infrastructure | Step 4: the key is minted with a spending limit held by OpenRouter |
| No-training routing, cost log, token ceiling | Shipped code | Step 5: templates/ai/ai.ts copied into the project |
The guarantee is structural: every skill goes through here, so no call can escape them. It is never enforced by policing the user's code.
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 · 342 lines · 53 tokens per session scan B 130a0761cc5b
_ensure-ai is a skill published in the GitHub repository flavien-ia/hypervibe-harness (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 4,330 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…