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 slavb18/rzd-api --skill find-full-compartmentgit clone --depth 1 https://github.com/slavb18/rzd-apiWrote 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/slavb18/rzd-api/find-full-compartment)<a href="https://agentmods.dev/skills/slavb18/rzd-api/find-full-compartment"><img src="https://agentmods.dev/badge/skills/slavb18/rzd-api/find-full-compartment.svg" alt="Measured on agentmods" 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 | $0.00121 | $0.01054 |
| Opus 5 | $0.00060 | $0.00527 |
| Sonnet 5 | $0.00024 | $0.00211 |
| Haiku 4.5 | $0.00012 | $0.00105 |
Grade A, and why
find-full-compartment 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 7d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find a full train compartment
Reading the request
A request names a direction, a period and sometimes a party size: "Москва → Владивосток, полное купе, с 1 по 30 сентября 2026 с картинкой" carries all three. Fill the rest in yourself and say what you assumed - do not interrogate the traveller for parameters that have an obvious default.
- Party size. "Полное купе", "целое купе", "купе целиком" mean four berths
unless a number is given. "СВ" or "купе на двоих" means two: pass it as
places, because a two-berth carriage has two berths behind its door and four would never be confirmed there. - Period. Convert to an inclusive ISO range. A bare month means the whole month, "ближайшие даты" means from today. Ranges are capped at 31 days: if a longer one is asked for, search the first 31 days and say the range was cut.
- Drawing. Show it by default for the best match. "С картинкой", "покажи схему", "где именно места" all confirm it; only skip it if the traveller asks for text alone.
Ask a question only when the direction is genuinely ambiguous - "Владивосток"
resolves to two station codes, so find_stations first and pick or ask.
Answering
- Call
search_full_compartmentsonce with the direction, the ISO range andplaces. It returns the three nearest options and stops looking there, which is what someone planning a trip wants; passmax_resultswhen a number is asked for ("покажи 5 вариантов"). - Report only
confirmedentries as a compartment. Each carries the car and compartment number and the exact berths the carriage response listed inside that compartment. - Never promote a
candidatesentry. A candidate is a carriage with enough free berths that the API did not confirm as one compartment, and itsreasonsays why:places_not_in_one_compartment- the berths sit in different compartments; offer them as separate seats, never as a compartment;compartment_layout_missing- the response carried no compartment breakdown; say the compartment could not be confirmed. When nothing is confirmed, say so plainly and offer the candidates as what they are, or suggest widening the range.
- Earliest dates first. Give train, local departure and arrival, car, compartment, berths, service class, price per berth and total.
- Keep the berth markers exactly as returned:
36Жis a berth in a women-only compartment,6Сone in a mixed compartment. The traveller sees these on the ticket, so never strip them to the bare number - and mention what the marker means, since a women-only compartment changes who can travel there. - For the best match, call
get_car_schemewith that car's metadata fromget_carriages,include_image: trueand the compartment's berths infree_places. Withoutfree_placesevery berth stays the same near-white and the drawing reads as an empty carriage. The reply carries a PNG of about 60 KB;imageUrlsalso holds a link to the original drawing. - State the
checkedAttimestamp and warn that availability and prices change in real time. - Report every entry in
errorsand every date inuncheckedas a date that was not searched, never as a date with no compartments.uncheckedholds the dates the scan stopped short of, either because enough options were found or because it hit its request budget. On "покажи ещё" or "а на следующие даты", search again from the first date inunchecked. omittedcounts what was found and not returned. Mention it in one clause - "ещё 12 вагонов с той же причиной" - rather than listing everything.- Never claim to reserve or buy tickets; point to an authorized RZD sales channel.
What ships with it
1 file 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.
- 7d ago First seen · 69 lines · 121 tokens per session scan A 4c6f953a912b
find-full-compartment is a skill published in the GitHub repository slavb18/rzd-api (0 stars, last pushed 22d ago), licensed MIT. It adds 121 tokens to every session and 1,054 once invoked, about $0.0006 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 2026-08-31.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…