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 borski/travel-hacking-toolkit --skill sutochnogit clone --depth 1 https://github.com/borski/travel-hacking-toolkitWrote 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/borski/travel-hacking-toolkit/sutochno)<a href="https://agentmods.dev/skills/borski/travel-hacking-toolkit/sutochno"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/sutochno/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/borski/travel-hacking-toolkit/sutochno"><img src="https://agentmods.dev/badge/skills/borski/travel-hacking-toolkit/sutochno.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 MCP Rug Pull · line 90 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00146 | $0.02301 |
| Opus 5 | $0.00073 | $0.01151 |
| Sonnet 5 | $0.00029 | $0.00460 |
| Haiku 4.5 | $0.00015 | $0.00230 |
Grade A, and why
sutochno 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 9d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sutochno Search
Search Sutochno.ru (СУТОЧНО.РУ) — a Russian short-term-rental marketplace
where you book apartments, rooms, and houses directly from owners and pay in
rubles, typically via Mir card or bank transfer. It's the natural fit
for Russian-speaking travellers booking stays in Georgia / the CIS, where
Airbnb and Booking have withdrawn or won't take Russian cards. It complements
the Airbnb MCP and the vrbo skill: those reach Western inventory, Sutochno
reaches the ruble-priced, owner-direct inventory those platforms miss.
Sutochno is NOT behind Akamai. Unlike the vrbo skill (which fights an
Akamai bot wall and must run headed), Sutochno's server-rendered city pages
load fine headless — there is no bot sensor to defeat. This skill still ships
on the toolkit's standard patchright-docker base (the same image every
browser skill builds on), but only for the bundled chromium + OS deps; it does
not need Patchright's stealth. Patchright is a drop-in Playwright fork, so the
browser API is identical. The default mode is headless; --headed is opt-in for
debugging.
The JSON API is auth-walled — we scrape pages instead. Sutochno's /api/*
endpoints (e.g. /api/geo/suggest) return 403 Application authentication failed without an app token the SPA computes client-side. So this skill does
not touch the API. It scrapes the server-rendered city pages, where the
listing cards are already present in the HTML.
City results live on SUBDOMAINS. Each city has its own host:
https://tbilisi.sutochno.ru/, https://batumi.sutochno.ru/,
https://kutaisi.sutochno.ru/, etc. The country directory
https://sutochno.ru/georgia lists the supported Georgian cities and links out
to https://{city}.sutochno.ru/<listingId> cards. Pass the city as a
subdomain keyword (--city tbilisi) or a full URL (--url).
No login required. Sutochno search results are public; the skill finds rentals and returns links only — it does not log in or complete a booking.
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.
- 9d ago First seen · 181 lines · 146 tokens per session scan A 22aaabfcd4e4
sutochno is a skill published in the GitHub repository borski/travel-hacking-toolkit (654 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 2,301 once invoked, about $0.0007 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
docs-builder
Reorg a docs corpus, split an oversized doc, search it, keep pages current, index them.
remember
Consolidate stashes + friction into project memory.
live-canvas
Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.
branch-review
Review a branch before merge [target] [level].
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
ship
Mechanical pre-deploy gate — tests, build, tree state.