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 vineetu/simple-host --skill skillgit clone --depth 1 https://github.com/vineetu/simple-hostWrote 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/vineetu/simple-host/skill)<a href="https://agentmods.dev/skills/vineetu/simple-host/skill"><img src="https://agentmods.dev/badge/skills/vineetu/simple-host/skill/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/vineetu/simple-host/skill"><img src="https://agentmods.dev/badge/skills/vineetu/simple-host/skill.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 | $0.00088 | $0.00841 |
| Opus 5.5 | $0.00035 | $0.00336 |
| Sonnet 5.5 | $0.00018 | $0.00168 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
simple-host-brain 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 today.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simple Host product knowledge (owner only)
The owner's private knowledge base at https://simple-host.app/v1/brain, rebuilt every hour and after
every deploy from the INTENT, FEATURES, PARITY and CHANGELOG files of both repos, plus design,
platform and release docs. It only reads. It answers only the owner's account; anyone else gets 403.
Ask it before answering any question about these products. Quote what it returns and name the source file. If it does not say, say so rather than guessing.
Sign in once
You need the owner's Simple Host API key, sent as the X-API-Key header. If you already keep one for
simple-host.app, use it. Otherwise sign in as the owner:
- Ask the owner for the email of their Simple Host account.
POST https://simple-host.app/v1/authwith{"email":"<that email>"}. They get a 6-digit code.- Ask them for the code, then
POST https://simple-host.app/v1/auth/verifywith{"email":"<email>","code":"<code>","choose_handle":true}. The answer carriesapi_key. - Keep the key in your own secret store. Never show it, and never put it in a page or a file you share.
A 403 with owner_only means the key belongs to some other account: only the owner's works.
Ask
GET https://simple-host.app/v1/brain lists the tools with their arguments and says when the
knowledge was built. Each tool is POST https://simple-host.app/v1/brain/<tool> with a JSON object of
arguments and Content-Type: application/json; the answer is {"text": "...", "result": {...}}.
| Tool | Use it for | Arguments |
|---|---|---|
product_overview |
what a product is, who it is for, non-goals, current version, freshness | product: host, hack, enterprise, selfhost-host, selfhost-hack, hack-companies or all |
feature_lookup |
does a feature exist, how it works, its parity row | query |
parity |
which edition has a feature, or the whole table | feature (optional) |
decisions |
dated owner decisions and their reasons | query, since (2026-10-13 or 3d), product, limit (all optional) |
recent_changes |
what changed lately (default the last 7 days) | since, product, limit (optional) |
search |
full-text search over every source | query |
get_doc |
read a document or one section | path such as simple-host/PARITY.md, section (optional) |
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.
- today First seen · 53 lines · 0 tokens per session scan A fa4c17970fb4
simple-host-brain is a skill published in the GitHub repository vineetu/simple-host (1 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 841 once invoked, about $0.0004 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 2026-10-16.
Other skills, from other repositories
quiz-me
Quiz the user on root cause and intended fix BEFORE writing any non-trivial code, then verify comprehension of every change after. Use when the user asks for a bug fix, refactor, or feature and wants to stay technically sharp instead of vibe-coding. Also use when the user says "quiz me", "don't let me vibe code", or…
craft
Engineering standards for any code work on any stack — writing production code, slicing and reviewing PRs, authoring tests, running gates, merging, and running agent fleets. Load before touching code, not after review flags it.
personal-voice-capture
Use when a user wants an agent to learn, encode, or improve their personal writing voice as a reusable skill through source-text ingestion and iterative calibration edits.
demo-video-factory
Generate a custom 26s product-demo video from any SaaS URL — brand-matched scenes, a recreated product-UI "wow" scene, real screenshots, and a soundtrack. Use whenever the user wants a demo, promo, launch, or marketing video for a website or product.
servo-gate
Verify an artifact (a spec, a plan, a diff, a claim) against a named oracle from the project manifest, using a reviewer that did not produce it. Returns GO / FIX / STOP. Use before accepting a spec or plan, or before merging.
servo-flow
The servo process for a piece of work, phase by phase. Use at the start of any non-trivial task to know which phase you are in and which skill to run next.