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 Vladimir-Human/ru-marketplace-mcp --skill cian-connectorgit clone --depth 1 https://github.com/Vladimir-Human/ru-marketplace-mcpWrote 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/vladimir-human/ru-marketplace-mcp/cian-connector)<a href="https://agentmods.dev/skills/vladimir-human/ru-marketplace-mcp/cian-connector"><img src="https://agentmods.dev/badge/skills/vladimir-human/ru-marketplace-mcp/cian-connector/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/vladimir-human/ru-marketplace-mcp/cian-connector"><img src="https://agentmods.dev/badge/skills/vladimir-human/ru-marketplace-mcp/cian-connector.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 | $0.00159 | $0.02257 |
| Opus 5.5 | $0.00064 | $0.00903 |
| Sonnet 5.5 | $0.00032 | $0.00451 |
| Haiku 4.5 | $0.00016 | $0.00226 |
Grade A, and why
cian-connector 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 15d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cian Connector
Reads Cian through the site's own JSON API, called from inside the operator's
Chrome over CDP: the search endpoint answers an in-page POST, and the offer
card embeds its whole state in window._cianConfig. No HTML is parsed. Plain
HTTP is blocked by Cian's WAF on IP reputation (a 403 «Обнаружен подозрительный
трафик» page, no captcha), so there is no anonymous tier.
When to use
- Find offers by filters: deal (sale / long-term rent / daily rent), property type, region, rooms, price range, total area
- One offer's price, its price history, layout, building, address, metro, description and publisher
- Real estate only. For goods use the marketplace connectors; for price
comparison across shops use
compare_prices— Cian takes no part in it
Tools available
cian_search(deal, offer_type="flat", region=None, rooms=None, price_min=None, price_max=None, area_min=None, area_max=None, page=1)— offers viasearch-offers-desktop, 28 per page.dealissale,rent(long-term) ordaily(посуточно);offer_typeisflat,room,houseorcommercial.price_rubis None for an offer without a stated price — never 0, andprice_unitsays what it buys.cian_card(offer_id_or_url)— one offer: price,price_history, rooms, areas, floor, building, address,metro[], description, views,agent.
Not an MCP tool: cian_selfcheck() is a tri-state drift canary. It is
CLI-only — marketplace-mcp doctor runs every connector's canary at once.
Region is an id, not a name
Cian addresses regions by its own numeric ids. The connector knows only the four
below (KNOWN_REGIONS, used in error messages); any other id must come from cian.ru.
Known and verified live:
| id | region |
|---|---|
| 1 | Москва |
| 2 | Санкт-Петербург |
| 4593 | Московская область |
| 4588 | Ленинградская область |
Anything else needs the Cian id (visible as region= in a cian.ru search
URL). Do not guess an id: a wrong one returns another region's offers with
correct-looking prices. Default is CIAN_REGION (1, Moscow).
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.
- 15d ago Changed · +1 lines 9b462d8dc59e
- 1mo ago First seen · 145 lines · 159 tokens per session scan A a6407fb524dc
cian-connector is a skill published in the GitHub repository Vladimir-Human/ru-marketplace-mcp (163 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 2,257 once invoked, about $0.0006 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 2026-09-11.
Other skills, from other repositories
flow-next-flow
Use first in a Flow-Next repo for a spec id, change, bug, issue, slow code or metric, cleanup, design fork, dump to explain, repeated mistake, prompt change, what could break, what next. No quick asks.
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.
flow-next-prime
Assess codebase agent and production readiness. Classifies the project, verifies commands run, leads with a verdict and ranked next actions.